Good morning, Alex Chen ✨

Sat 21 Nov Β· here's where everything stands.

Today

2
  • The reconciliation report is signed off (pf-101)
  • The load-test plan is agreed with SRE (pf-104)
  1. 1Billing dual-write reconciliation report (cutover go/no-go)pf-101platformP0due 23 Nov
  2. 2Quarterly access reviews (SOC 2 evidence)cp-031complianceP1due 25 Nov

Carried over Β· 1

  1. ↻Fix timezone rounding in the legacy billing exporterpf-099platformP1from Fri 20

Due, not planned Β· 1

  1. !Send the board the activation funnel numbersgr-014growthP1due 21 Nov

Roadmap

4
  1. !M1Billing shadow modev2 launch1 of 2 donewindow ended 31 Octpf-097 donepf-099 carried over
    ⏳ Legacy exporter rounding fix (pf-099)
  2. β—†M2Launch gatev2 launch0 of 2 donepf-101 todaypf-104 week
    ⏳ Reconciliation report and go/no-go (pf-101)
  3. β—†M3SOC 2 evidencev2 launch0 of 2 donecp-031 todaycp-028 month
    ⏳ Quarterly access reviews (cp-031)
  4. β—†M4Public status pagev2 launch1 of 2 doneno open task behind it

This week

2
  • platform: Ship the reconciliation report (pf-101)
  • platform: Run the 5x load test (pf-104)
  • growth: Empty-state redesign (gr-012)
1 of 6 done
  1. Β·v2 load test at 5x peak (launch gate)pf-104platformP0due 24 Nov
  2. Β·Empty-state redesign (activation step-2 leak)gr-012growthP1due 29 Nov
  3. βœ“Dual-write shadow mode for usage billingpf-097platformP1

This month Β· November

1
1 of 7 done
  1. Β·Vendor inventory and DPA sweepcp-028complianceP2due 9 Dec

Queue

5
My pull requests Β· 3
Reviews I owe Β· 2

Later

1
  1. Β·Push-notification opt-in experimentmb-034mobileP2blocked: Needs 3.2 live (mb-032).

Not planned

1
  1. Β·Mobile 3.2 App Store review and releasemb-032mobileP1due 25 Novblocked: Submitted; waiting on Apple review (typically 2 to 4 days).

πŸ’¬ Sessions Β· 3

15m agoBilling reconciliation walk
Waiting on the exporter fix
πŸ”— pf-099 Fix timezone rounding in the legacy billing exporter
πŸ”— pf-101 Billing dual-write reconciliation report (cutover go/no-go)
↳ claude --resume 3f1c9a2e-5b7d-4e21-9c0a-8d4b2f6e1a90
yesterdayLoad-test target
next: run the load test on Thursday
↳ claude --resume 7b2e4d91-0c3a-4f6e-8a15-2d9c7e4b1f38
2 days agoSOC 2 evidence sprint
Access reviews 4 and 5
↳ claude --resume c94a1e27-6d8b-4b3f-9e02-5a7f1c3d8e64

✏️ Tasks touched · 6

pf-101Billing dual-write reconciliation report (cutover go/no-go)activeplatform
pf-104v2 load test at 5x peak (launch gate)openplatform
gr-014Send the board the activation funnel numbersopengrowth
cp-031Quarterly access reviews (SOC 2 evidence)activecompliance
gr-012Empty-state redesign (activation step-2 leak)activegrowth
pf-099Fix timezone rounding in the legacy billing exporteropenplatform

⚑ Commands · 2

01:27/agentlayer:sync
22 turns
β€”yesterday/agentlayer:briefing evening
11 turns

πŸ“° Output Β· 6

Goalsfrom projects/TASKS.md

β˜€οΈToday 2

1
The reconciliation report is signed off (pf-101)
2
The load-test plan is agreed with SRE (pf-104)

πŸ—“This week 3

Week of 16 Nov

1platform
Ship the reconciliation report (pf-101)
Done whengo/no-go signed off
2platform
Run the 5x load test (pf-104)
Done whenp99 under 300 ms at peak
3growth
Empty-state redesign (gr-012)
Done whenvariant B live to 50%

🎯This month 0

v2 launched with zero Sev-1s in week one

No goals set for this month, run goals month.

🧭This year 0

No goals set for this year, run goals year.

2026-11-21

Tasks

9 open tasks across 4 projects, by deadline.

0overdue
none

β–Ά In flight Β· 3

pf-101Billing dual-write reconciliation report (cutover go/no-go)platformπŸ’¬ 1due in 2dP0
statusactivedue2026-11-23updated2026-11-21
cp-031Quarterly access reviews (SOC 2 evidence)complianceπŸ’¬ 1due in 4dP1
statusactivedue2026-11-25updated2026-11-21
gr-012Empty-state redesign (activation step-2 leak)growthπŸ’¬ 1due 2026-11-29P1
statusactivedue2026-11-29updated2026-11-20

πŸ“… Due today Β· 1

gr-014Send the board the activation funnel numbersgrowthπŸ’¬ 1due todayP1
statusopendue2026-11-21updated2026-11-20

πŸ—“ Due this week Β· 2

pf-104v2 load test at 5x peak (launch gate)platformπŸ’¬ 1due in 3dP0
statusopendue2026-11-24updated2026-11-20
mb-032Mobile 3.2 App Store review and releasemobileπŸ’¬ 1due in 4dP1
statusblockeddue2026-11-25updated2026-11-19
blocked bySubmitted; waiting on Apple review (typically 2 to 4 days).

πŸ“† Due this month Β· 1

cp-028Vendor inventory and DPA sweepcomplianceπŸ’¬ 1due 2026-12-09P2
statusopendue2026-12-09updated2026-11-09

β™Ύ No due date Β· 2

pf-099Fix timezone rounding in the legacy billing exporterplatformπŸ’¬ 1P1
statusopenupdated2026-11-21
mb-034Push-notification opt-in experimentmobileπŸ’¬ 1P2
statusblockedupdated2026-11-19depends onmb-032
blocked byNeeds 3.2 live (mb-032).

β›” Blocked Β· 2

mb-032Submitted; waiting on Apple review (typically 2 to 4 days).mobile
mb-034Needs 3.2 live (mb-032).mobile

πŸ‚ Going stale Β· 1

cp-028Vendor inventory and DPA sweepcomplianceπŸ’¬ 1due 2026-12-09P2
statusopendue2026-12-09updated2026-11-09

Projects

4 projects β€” click one to see its tasks.

4projects
4 with live tasks
4moving
updated in 7 days
0quiet
no live tasks
18%done overall
2 of 11 tasks
platform1 active Β· 2 openupdated 15h ago
Core API, billing, and infrastructure. Owns the v2 launch and the usage-based billing migration.
β˜‘ 1 / 4
25%

β–Ά Active Β· 1

pf-101Billing dual-write reconciliation report (cutover go/no-go)πŸ’¬ 1due in 2dP0
statusactivedue2026-11-23updated2026-11-21

β—‹ Open Β· 2

pf-104v2 load test at 5x peak (launch gate)πŸ’¬ 1due in 3dP0
statusopendue2026-11-24updated2026-11-20
pf-099Fix timezone rounding in the legacy billing exporterπŸ’¬ 1P1
statusopenupdated2026-11-21
compliance1 active Β· 1 openupdated 15h ago
SOC 2 Type II track. Audit fieldwork starts in four weeks.
β˜‘ 0 / 2
0%

β–Ά Active Β· 1

cp-031Quarterly access reviews (SOC 2 evidence)πŸ’¬ 1due in 4dP1
statusactivedue2026-11-25updated2026-11-21

β—‹ Open Β· 1

cp-028Vendor inventory and DPA sweepπŸ’¬ 1due 2026-12-09P2
statusopendue2026-12-09updated2026-11-09
growth1 active Β· 1 openupdated 2d ago
Activation funnel, onboarding, and SEO. North star: weekly active workspaces.
β˜‘ 1 / 3
33%

β–Ά Active Β· 1

gr-012Empty-state redesign (activation step-2 leak)πŸ’¬ 1due 2026-11-29P1
statusactivedue2026-11-29updated2026-11-20

β—‹ Open Β· 1

gr-014Send the board the activation funnel numbersπŸ’¬ 1due todayP1
statusopendue2026-11-21updated2026-11-20
mobile2 blockedupdated 3d ago
iOS and Android shipping app (React Native). 3.2 is in App Store review.
β˜‘ 0 / 2
0%

β›” Blocked Β· 2

mb-032Mobile 3.2 App Store review and releaseπŸ’¬ 1due in 4dP1
statusblockeddue2026-11-25updated2026-11-19
blocked bySubmitted; waiting on Apple review (typically 2 to 4 days).
mb-034Push-notification opt-in experimentπŸ’¬ 1P2
statusblockedupdated2026-11-19depends onmb-032
blocked byNeeds 3.2 live (mb-032).

Sessions

What you and Ace worked on, captured automatically.

Volumelast 7 days

Sun 597 BMon 407 BTue 692 BWed 502 BThu 230 BFri 261 BSat 481 B

Latest radar2026-11-21 01:29 Β· open

Launch-week prep across three threads: billing reconciliation, the load-test harness, and SOC 2 evidence.

🟒 In motion (last hour)

1. Billing reconciliation walk Β· 15m ago

βœ“ Week-1 dual-write numbers reviewed (41 mismatches counted)
βœ“ Exporter's timezone rounding explains all 41 (filed as pf-099)

β–Ά Waiting on the exporter fix
β–· next: rerun the week-1 comparison once pf-099 lands

πŸ”— pf-099 Fix timezone rounding in the legacy billing exporter
πŸ”— pf-101 Billing dual-write reconciliation report (cutover go/no-go)
↳ claude --resume 3f1c9a2e-5b7d-4e21-9c0a-8d4b2f6e1a90

πŸ• Earlier

2. Load-test target Β· yesterday

βœ“ Settled 5x over 10x (agreed in the thread)
βœ“ Staging booked for Thursday (calendar invite sent)

β–· next: run the load test on Thursday

↳ claude --resume 7b2e4d91-0c3a-4f6e-8a15-2d9c7e4b1f38

3. SOC 2 evidence sprint Β· 2 days ago

βœ“ Access reviews 3 of 5 done (signed off)
βœ“ Okta checklist drafted (assumed)

β–Ά Access reviews 4 and 5
β–· next: chase the two remaining reviewers

↳ claude --resume c94a1e27-6d8b-4b3f-9e02-5a7f1c3d8e64
3 sessions Β· 24h window Β· scoped to ~/agent-acme

2026-11-21

27 turns
build the empty-state variant behind a flag; the design link is in gr-012
9 turns
prep interview debrief notes for the two platform onsites and compile them into the hiring doc
35 turns
fix the exporter timezone rounding and replay the 41 mismatched invoices as a regression test
14 turns
draft the okta access review from the export and flag anything stale

2026-11-20

19 turns
should the load test target 10x or 5x peak
42 turns
reconciliation dashboard: match rate by day and a drilldown into mismatches
15 turns
confirm the funnel numbers on production before we brief the board

2026-11-19

31 turns
soc2 evidence sprint: pull the access lists and draft the review docs
24 turns
walk the 3.2 release checklist with me before we submit
~/agent-acme2 sessions2026-11-21
~/acme/web1 session2026-11-21
~/acme3 sessions2026-11-21
~/acme/platform3 sessions2026-11-21
~/acme/growth1 session2026-11-20
~/acme/mobile1 session2026-11-19

Brain

Ace's living memory of your world β€” compiled from every session.

0pending compile
last compiled 31m ago

Context loaded every session8 sources Β· 41.4 KB

instructions 33.8 KBidentity 2.3 KBknowledge 2.7 KBtasks 2.6 KB
sourcesize
βœ“.claude/CLAUDE.md project2.3 KB
βœ“AGENTS.md31.5 KB
βœ“SOUL.md718 B
βœ“IDENTITY.md1.1 KB
βœ“USER.md501 B
βœ“knowledge/index.mdThe master catalog β€” a table of contents for the whole knowledge base. It lists every permanent article with a one-line description, so Ace can find and load just what it needs on demand instead of pulling the entire brain into context every session.752 B
βœ“knowledge/memory/index.mdAce’s long-term memory: active threads, recent decisions, learnings, and key context distilled from past sessions during compile (the β€œdreaming” step). Loaded every session so Ace wakes up knowing where things stand.2.0 KB
βœ“projects/TASKS.mdA high-level overview of every task across projects β€” priorities, what’s overdue, what’s being worked on right now. A distilled snapshot, not the full per-task detail, so Ace sees the lay of the land without loading every task file.2.6 KB

Path-scoped rules3 active

ruleapplies tosize
mobile project
apps/mobile/**
88 B
sql project
**/*.sql**/migrations/**
106 B
typescript project
**/*.ts**/*.tsx
114 B

Injected at SessionStart1.6 KB

entrysize
βœ“today's date Saturday, November 21, 2026
βœ“session tail 2026-11-21.md453 B
βœ“today's reports 3 entries353 B
β—‹pinned reports none pinned0 B
βœ“history 1 snapshot45 B
⚠host versions update the host0 B

Daily memory14-day retention

2026-11-21Reconciliation walk; exporter bug root-caused and filed as pf-099.
2026-11-20Load-test target locked at 5x; reconciliation dashboard specced.
2026-11-19SOC 2 evidence sprint; 3.2 release checklist walked and submitted.

Learningshow Ace self-corrects

Lead with the number. Alex reads the first line only unless it earns the rest.
Never page before checking the runbook.
Staging data is not production data; confirm funnel numbers on production before a board brief.

Pendingopen loops Ace is tracking

pf-104 load test Β· staging booked for Thursday.
cp-031 access reviews Β· 3 of 5 systems done; Okta and AWS remain.
Senior platform engineer hire Β· two onsites this week.

Active threads5 live

πŸš€ v2 launch Β· window locked for 2026-12-05; marketing page staged, changelog drafted. pf-104 load test is the last gate.
🎯 SOC 2 Type II · fieldwork starts 2026-12-19; evidence 80% done, cp-031 due this week.
🚨 Billing migration (Stripe to usage-based) · dual-write live since 2026-11-15; cutover gated on pf-101.
πŸ“± Mobile 3.2 Β· in App Store review; the push opt-in experiment is queued behind it.
πŸ“ˆ Activation leak Β· step-2 drop-off 38% to 31% after the email rework; gr-012 is the next lever.

Recent decisions

2026-11-20 β€” Load test at 5x peak, not 10x: 10x costs three extra days and the v2 traffic model doesn't justify it.
2026-11-19 β€” Billing cutover hard date set, gated on the dual-write reconciliation report.
2026-11-17 β€” Incident runbooks live in the brain, not the wiki; every postmortem ends with a runbook diff.
2026-11-15 β€” Two-pass agent code review team-wide.
2026-11-12 β€” Empty-state redesign over the pricing experiment: step 2 is the leak, not the paywall.
activation-funnel β€” Step-by-step activation model and where Acme leaks new workspaces
agentic-code-review β€” Two-pass agent review: correctness first, then simplification
brain-fed-planning β€” Weekly planning that starts from the compiled brain, not a blank doc
incident-runbook-loop β€” Every postmortem ends with a runbook diff in the brain

Compile pipelineΞ£ $4.76

sessions ingested7
pending0 β€” fully absorbed
last compiled31m ago
inbox to absorb1

Memory footprint

curated wiki4.7 KB
memory index2.0 KB
learnings3
daily memory files3 (14-day retention)
feedback log105 B

Last lint run2026-11-21T01:22:00-05:00

errors0
warnings1
suggestions1
reportopen lint.md

Issues2

WARNActive Threads bullet 1 is 262 characters (budget 250)
SUGGESTIONconcepts/brain-fed-planning has no inbound links

Reports

Briefings, plans, and audits Ace has produced. Click any title to open it.

2026-11-21

Scheduler ⏰

Recurring routines and when to run them β€” manual for now.

Sync (morning)manual
Daily Β· 07:00
next Sat, Nov 21 today
/agentlayer:sync
Sync (evening)manual
Daily Β· 19:00
next Sat, Nov 21 today
/agentlayer:sync
Weekly goalsmanual
Mondays Β· 08:00
next Mon, Nov 23 in 2d
/agentlayer:goals week interview
Monthly goalsmanual
1st of month Β· 08:00
next Tue, Dec 1 in 10d
/agentlayer:goals month
Yearly goalsmanual
Quarterly Β· Jan/Apr/Jul/Oct 1 Β· 08:00
next Fri, Jan 1 in 41d
/agentlayer:goals year
Self-reviewmanual
15th of month Β· 08:00
next Tue, Dec 15 in 24d
/agentlayer:self-review

Capabilities

Everything you can ask Ace to do β€” skills by name, tools under the hood.

whensaywhat happens
Morning and evening/agentlayer:syncFull refresh β€” compile, lint, flywheel, dashboard β€” then a briefing. Picks the briefing automatically: morning if none ran today (even in the afternoon), evening once it has or past 9pm (or say `sync morning` / `sync evening`).
Between sessions/agentlayer:briefing pulseA fast status check without the heavy maintenance pass.
Feeling lost/agentlayer:attention checkpoint allA checklist for each recent session β€” what got done, where it stands, what waits on you, how to resume it.
After a busy day/agentlayer:knowledge-compileAbsorb captured sessions, feedback, and inbox drops into long-term memory.
1st of the month/agentlayer:goals monthSet the month’s themes and big rocks (`goals week` does the same per week, `goals day` for today).
Quarterly/agentlayer:goals yearPlan the year ahead quarter by quarter β€” run mid-year it shapes the remaining quarters; run in Q4 it drafts next year from Q1.
Once a month/agentlayer:self-reviewSync asks when it is due. Cleans up stale tasks, quiet projects, outdated memory and articles with you, then turns your feedback into better rules.
Save anythingβ€œcapture this: <url, text, or file>”Drops it into the inbox; the next compile absorbs it into the wiki.
Jot something down/capture <text>Saved to the inbox at once, with no reply to wait for (Claude Code; `/lesson <text>` does the same for a correction).
Line up the next ask/queue <prompt>Sent once the current task ends, one per turn, never mid-task (Claude Code; `/queue clear` drops the rest).
Find what this session made/reportsThe reports and project pages this conversation wrote, in a row above the prompt (Claude Code; `/reports attach <path>` adds any file).
File workβ€œcreate a task in <project>: …”New task file with id, priority, and due date; shows up here and in TASKS.md.
Taxes and receipts/agentlayer:tax <what’s due | receipt | close | help>Tax deadlines as dated tasks, receipts filed to the ledger, monthly close for the accountant; nothing is filed or paid without you.
Support queue/agentlayer:helpdesk pulseOpen tickets ranked, patterns across them and tickets to raise, saved to reports/helpdesk/; replies are drafted as private notes, never sent.
Grab a pageβ€œscreenshot https://…”Headless-browser PNG into reports/captures/.
Make a PDFβ€œturn <file or url> into a styled PDF”Markdown/page rendered to PDF (mermaid included) in reports/captures/.
Research somethingβ€œresearch <topic> and write it up”Web research with sources, persisted as a report you can reread.
Reviewing a PR/agentlayer:engineer review <number>Verified findings with paste-ready comments for a teammate’s PR; `engineer replies <number>` drafts replies and uncommitted fixes for your own. Reports land in reports/reviews/.
Presenting or recording your own PR/agentlayer:engineer walkthrough <number>Standup script, diff tour in scroll order, the questions reviewers will ask with receipts, and a scene-by-scene recording runbook for your PR. Lands in reports/reviews/.
Second model’s pass on your work/agentlayer:adversarial-reviewWrites the brief another model reviews from (a PR, a branch, an uncommitted tree, or a plan), then verifies its findings, fixes the real ones, and refreshes the brief; one dossier in reports/reviews/ for every round.
Refresh this page/agentlayer:dashboardRegenerates this dashboard (and TASKS.md) from current state.
/agentlayer:adversarial-review auto
Cross-model adversarial review of your own work, as a loop on one dossier in `<HOME>/reports/reviews/`: a PR, a branch, an uncommitted working tree, or a plan,…
/agentlayer:api-collections auto
Draft API requests as collection files the operator opens, visualizes, and fires in their API client (adapters β€” Bruno and Postman shipped, plain-curl fallback…
/agentlayer:attention auto
The operator's day in one place: what today is for, what slipped, the week and month, the roadmap in flight, who is waiting on them, and where each session lef…
refreshaddplanorganizestandupcheckpointbackfill
/agentlayer:briefing auto
The day's bookends and a quick check.
morningeveningpulse
/agentlayer:browser-flows auto
Drive a website in a VISIBLE browser to run real, repeatable flows end to end β€” scrape a page into structured data, fill a form, or click through a multi-step …
/agentlayer:configure-skills auto
Configure the agent's optional skill packs (SEO, Browser, Database, GitHub, API, Xcode, Helpdesk, App Store, Slack, cmux) or author a brand-new custom skill.
/agentlayer:dashboard auto
Refresh and open the Agent OS dashboard β€” a static HTML mission-control page covering today's attention view and activity, work across projects, sessions, the …
/agentlayer:discuss
Talk one task or goal through with the operator before anything is built - where it stands, what's unknown, the ways forward - then end on a choice of next mov…
/agentlayer:engineer auto
Engineering rigor for code work in a repository: fix a bug, build or change a feature, refactor or simplify, chase a slowdown or hillclimb a metric, prototype …
investigationhowwhybug fixfeaturesimplifyrefactoringperformancehillclimbruntime forensicstrace forensicsvisual parityblast radiusprototypefigure it outautonomous runpause safelysession pickupauthoring a skillevalverification skillpr reviewpr repliespr walkthroughgithub sweep
/agentlayer:find-session auto
Find a past session by what it worked on β€” a branch, a PR number, a worktree, a bug, a feature, a task id β€” and hand back its resume command or its notes from …
/agentlayer:flywheel auto
Cross-project work session.
/agentlayer:goals auto
Goals from today to the year, written to the goal blocks in TASKS.md; the attention skill plans the days around them.
dayweekmonthyear
/agentlayer:guide auto
Write a guide someone else can follow as a polished HTML page: a setup walkthrough, onboarding, or how a workflow runs end to end and who does what.
/agentlayer:helpdesk auto
SupportCandy or Pylon tickets.
setuppulsestatsticketaccountdraftreviewsraiseworkflow
/agentlayer:history auto
Turn on version history for the agent's memory, so any change to what it knows can be seen and undone.
/agentlayer:humanizer auto
Remove signs of AI-generated writing from text.
/agentlayer:init
Guided first-run onboarding for the agentlayer plugin.
/agentlayer:itinerary auto
Plan a trip end-to-end and generate a polished, interactive, print-ready HTML itinerary.
/agentlayer:knowledge-compile auto
Compile raw session logs, feedback, and inbox items into structured wiki articles.
/agentlayer:media auto
Make sense of a local audio or video file: transcribe the speech on-device with timestamps, grab screenshots, summarize what was said and shown, turn a bug-rep…
summarizetickettranscribescreenshotsremember
/agentlayer:mermaid auto
Validate and iterate on a Mermaid diagram before it ships.
/agentlayer:plan-spec auto
Deep-dive specification writer that reads input files, interviews the user with Socratic questioning, and produces a comprehensive spec document.
/agentlayer:project auto
Start, retire, or hand off project work.
createarchivehandoff
/agentlayer:proposals
The heartbeat's wake, run by its own clock in the session /heartbeat chose (or with /heartbeat now) - look at tasks, the brain, GitHub, live sessions and every…
/agentlayer:release
Producer-only.
/agentlayer:rename-agent
Rename this agent's display name across an existing HOME β€” the Name in IDENTITY.md, the emoji and avatar, and every mention in the markdown the agent reads now…
/agentlayer:roadmap auto
Build or update a strategic roadmap as a polished, self-contained HTML surface β€” timeline lanes over a directional rail, milestone cards, outcome bands, dark/l…
/agentlayer:seed auto
Hand this agent to a teammate, or take one on.
exportimport
/agentlayer:self-review auto
Monthly upkeep of the agent's brain and rules, with the operator.
brainrules
/agentlayer:seo auto
Search evidence for a site, read-only: a full audit (Search Console + PageSpeed + on-demand SERP checks, ranked findings, a written report), Search Console que…
auditconsolespeedserprank
/agentlayer:setup-worktree auto
Create a git worktree for parallel work, as a sibling of the repo, and bootstrap it ready to code: copies the gitignored local files from the main checkout, in…
/agentlayer:slack auto
Read-only Slack, never posts.
/agentlayer:sync auto
End-to-end refresh β€” fast-forward configured code repos, compile pending raw inputs, lint and fix the wiki, run a flywheel pass, surface what needs attention (…
/agentlayer:tax auto
Bookkeeping and tax compliance for the operator's companies and personal return: what tax is owed right now, deadlines as dated tasks, receipt capture, monthly…
setupcalendarpositioncapturecloseestimateaccountantoptimizeyear-end
/agentlayer:upgrade auto
Apply pending HOME migrations after a plugin code update.
/agentlayer:wordpress-rest auto
Query WordPress content via the public WP REST API β€” posts, pages, custom post types, categories, tags, media, and modified dates.
appstore_reviews
Read App Store reviews for any app, newest first: rating, title, text, the reviewer's nickname, app version, date and storefront, with rating counts.
attention_write
Render attention (today, carried over, this week, this month, the roadmap in flight, and a queue of what's waiting on the operator).
browser_flows
Run a browser-flows flow that drives a site in a VISIBLE browser (the operator can log in manually when a flow needs it β€” no API keys).
browser_markdown
Render a URL or local file in chromium so JS-rendered content hydrates, then extract the article body via Mozilla Readability and convert to Markdown.
browser_pdf
Render a URL or local file (HTML or Markdown) to PDF.
browser_record
Drive a browser through scripted steps and return a video file.
browser_screenshot
Capture a PNG screenshot of a URL or local HTML/MD file.
capture
Capture any input (a thought, snippet, dropped file, URL) into the agent's raw tree for the next knowledge-compile to absorb.
codex_setup
Generate or regenerate this home's Codex wiring (.codex/hooks.json, the MCP registration and permission profile in .codex/config.toml, and .codex/rules/agentla…
compile_next
Return the next compile work item: a rendered prompt + source content + metadata.
compile_status
How many raw items are pending compilation (sessions/feedback/inbox).
compile_write
Mark a compile work item complete.
curl_run
Fire ONE curl request with collection-scoped secrets, returning transcript-safe output.
dashboard
Rebuild both derived views in one pass: projects/TASKS.md (task dashboard from frontmatter β€” Active, Blocked, Overdue, Stale, Recently Closed; preserves the go…
database_fork
Fork (clone) a database on a LOCAL Postgres server so you can make heavy or destructive schema changes without touching the shared/live one β€” for a worktree, a…
database_list 0 databases
List the Postgres connections available to query.
database_query 0 databases
Run a read-only SQL query against a configured Postgres connection.
database_schema 0 databases
Inspect a Postgres database structure (read-only).
github_comment_update
Replace the text of your own comment on an issue or a pull request's conversation (writes to GitHub; the old text is gone).
github_fast_forward
Fast-forward the default branches (main||master and develop||dev) of the configured local checkouts so the agent grounds against current code.
github_issue_comment
Comment on a GitHub issue (writes to GitHub, visible to everyone with repo access), optionally with screenshots or videos attached.
github_issue_create
Open a GitHub issue (writes to GitHub, visible to everyone with repo access).
github_issue_list
List issues for a repo (read-only).
github_issue_update
Change a GitHub issue's title, description, labels or milestone (writes to GitHub).
github_issue_view
View one issue in full (read-only): body, labels, assignees, milestone, comments, state/close reason, and timestamps.
github_pr_checks
Status of every check on a pull request (read-only): name, state, bucket (pass/fail/pending/skipping/cancel), workflow, and a link.
github_pr_comments
Every comment on a pull request (read-only): inline review threads with their file/line anchor and resolved + outdated state, review submission bodies, and top…
github_pr_create
Open a pull request from a branch already pushed (writes to GitHub, visible to everyone with repo access).
github_pr_diff
The unified diff of a pull request (read-only).
github_pr_list
List pull requests for a repo (read-only).
github_pr_update
Replace a pull request's title or description (writes to GitHub; the old text is gone).
github_pr_view
View one pull request in full (read-only): body, latest reviews, conversation comments, changed files, diff stats, label/review state, mergeability, the head c…
github_run_list
List GitHub Actions workflow runs for a repo (read-only).
github_run_log
Logs for a workflow run (read-only).
github_run_view
View one workflow run (read-only): overall status/conclusion plus the per-job, per-step breakdown so you can see which job and step failed.
github_sweep
Everything on one repo waiting on the operator (read-only): their open PRs, PRs requesting their review, PRs and issues they're involved in, and open issues as…
google_auth
One-time Google OAuth2 consent flow.
gsc_inspect
Inspect a single URL's indexing status via the URL Inspection API.
gsc_query
Search analytics rows for the configured site.
gsc_sites
List all sites/properties accessible to the authenticated GSC user.
helpdesk_accounts
List the helpdesk's accounts (customer companies): id, name, domains, tags and owner.
helpdesk_assign
Assign a helpdesk ticket to a teammate (an id from helpdesk_lookups teammates), so a person picks it up.
helpdesk_attachment
Download one ticket attachment (a log, a screenshot) by the id helpdesk_ticket listed, into a fresh temp folder outside the home, and return its path.
helpdesk_connections
List the configured helpdesk connections: each helpdesk, its connection name (absent for the default) and its site where that is not a secret.
helpdesk_lookups
List one kind of helpdesk reference data as id + name: statuses and categories (SupportCandy), teammates (both; with email on Pylon), tags and macros with thei…
helpdesk_note
Add a private note to a helpdesk ticket: visible to agents, never to the customer.
helpdesk_stats
Count the helpdesk tickets in the given statuses updated within a window (default the last 24h): total, by status, by tag (by category on SupportCandy; a ticke…
helpdesk_ticket
Fetch one helpdesk ticket with its whole conversation, oldest first: the ticket's opening body when the helpdesk keeps it apart, linked engineering issues and …
helpdesk_tickets
List helpdesk tickets updated within a lookback window, newest first: id, number, subject, status, category or tags, requester and assignee (name, email where …
home_history
Version history for this agent home.
knowledge_lint
Run structural health checks across the wiki (broken links, orphan pages, orphan sources, missing backlinks, sparse articles, transient memory refs in permanen…
links_rewrite
Normalize bare task IDs and shorthand references into [[wikilinks]] across the knowledge base.
list_worktrees
Audit every registered worktree of a repo β€” the accumulated-worktrees triage tool.
media_transcribe
Transcribe the speech in a LOCAL audio or video file, on-device (macOS 26+ via `yap`, `brew install yap`; audio never leaves the machine).
memory_prune
Delete daily memory files older than the retention window (default 14 days).
open_page_rank
Get OpenPageRank score for up to 100 domains.
page_speed_audit
Run PSI for both mobile + desktop in parallel.
page_speed_psi
Lighthouse PageSpeed Insights slice for one URL+strategy.
ping
Health check β€” returns server status, the plugin version this server process loaded, and resolved paths.
proposal_add
Propose sessions for the operator to start later, and retire showing ones a better candidate outranks, a live session already covers, or that are no longer tru…
remove_worktree
Tear down a git worktree safely, running outside the Bash sandbox so `git worktree remove` can write the main repo's .git/config.
report_write
Write a report file to reports/<category>/ AND insert a one-line entry into reports/index.md under today's date heading.
run_upgrade
Run the versioned upgrade migration at skills/upgrade/scripts/<version>.ts, outside the Bash sandbox (so it can touch deny-gated paths).
seed_export
Build a seed bundle zip from an APPROVED selection β€” call only after the seed export interview + per-file review gate.
seed_import
Overlay a seed bundle onto THIS initialized home (fork semantics β€” imported files become the recipient's own).
seed_scan
Read-only: detect what this home could hand a teammate as a seed bundle β€” agent name (custom vs template), identity divergence, concepts (template-identical fl…
serpapi_search
Real Google SERP data: organic results, ads, AI overview, shopping, PAA, knowledge graph.
setup_worktree
Create a sibling git worktree and bootstrap it (copy gitignored local files β†’ install deps β†’ build), running outside the Bash sandbox so git can write .git/con…
slack_batch_history
Fetch recent messages from many Slack channels in one parallel call.
slack_channels
List the Slack channels the operator is a member of (sorted by name).
slack_history
Fetch recent messages from one Slack channel (by #name or channel ID).
slack_search
Search Slack messages across the workspace.
slack_thread
Fetch a full Slack thread (root message + replies).
slack_waiting
What Slack is waiting on, read-only: `external`, threads in the given channels whose last word is from outside the workspace (another organization in a shared …
slack_whoami
Verify Slack access and return the authenticated identity (user, team, scopes, token expiry) with `connected: true`, or `connected: false` and a hint when this…
task_close
Close a task as done (status=done, closed=today).
task_create
Create a new task.
task_get
Read a single task file in full (frontmatter + description + checklist + thread).
task_query
List tasks across all projects, optionally filtered by status/priority/project/assignee/horizon lane.
task_scan
Resolve cross-task state: auto-unblock, auto-block, surface overdue, due-soon (next 14 days) and stale tasks, plan priority bumps.
task_thread
Append a message to a task's thread section.
task_update
Update fields on an existing task.
video_frames
Extract still frames from a LOCAL video file for visual analysis, running outside the Bash sandbox so it can read videos in ~/Downloads, ~/Desktop, ~/Documents…
web_search
Search the web via Perplexity.

Usage

${CLI_COMMAND} <group> <command> [flags]

Groups

ping
Print resolved paths + timezone (sanity check)
colors [--line=<1-4 | "#RRGGBB #RRGGBB">]
Show the color pairs an agent can take, each in its own colors; --line prints a choice's IDENTITY.md Colors value (exit 2 when it isn't a pair number or two codes). Read-only
hosts
Check the installed Claude Code / Codex CLIs against the plugin's version floors (--codex: require Codex); exit 1 below a floor
capture
Capture text / a file / stdin into raw/inbox/ (or feedback.md) for the next compile
session-capture
Ingest a session transcript into raw/sessions/<today>.md (called by Claude Code hooks)
session-start
Emit dynamic context (today / last session tail / git activity) for the host's SessionStart hook
statusline
Render Claude Code's footer from the status-line JSON on stdin (--setting: the settings entry)
task
Read + mutate task files under projects/*/tasks/
compile
Knowledge-compile state (synthesis runs in Claude Code, not here)
knowledge
Wiki maintenance (lint)
notices
What to nudge the operator about (upgrade, sync) as JSON; \`notices record <id> --outcome=acted|snoozed\` logs what they did
proposals
Sessions the agent proposes and the heartbeat that keeps them coming: list, decide, heartbeat
prune
Delete memory/YYYY-MM-DD*.md older than 14 days
links
Rewrite bare task IDs + shorthand into [[wikilinks]]
dashboard
Rebuild the Agent OS dashboard at <HOME>/dashboard.html + projects/TASKS.md (open in any browser)
worktree
Create a sibling git worktree of <repoPath> and bootstrap it (copy locals β†’ install β†’ build); \`worktree remove\` tears one down safely
seed
One-shot agent handoff: scan what this home could seed a teammate with, export a reviewed selection as a zip bundle, import a bundle into a fresh home
database
Query/inspect/fork local Postgres via AGENT_DB_<NAME> connections (real terminal β€” outside the Bash sandbox)
cmux
The optional cmux pack: the AgentLayer sidebar, one per Mac, that every home on it joins

Task commands

task query [--status=X] [--priority=P0-P3] [--project=NAME]
task get <id>
task create --project=NAME --title=... --description=... [--priority=P2] [--type=task|bug|idea|epic] [--due=YYYY-MM-DD] [--horizon=today|week|next-week|month|later] [--labels=a,b] [--depends_on=id1,id2] [--parent=ID] [--checklist=item ...]
task update <id> [--status=X] [--priority=X] [--title=X] [--due=YYYY-MM-DD] [--horizon=X] [--blocked_by=X] [--labels=a,b] [--depends_on=id1,id2] [--parent=ID] [--issue=URL] [--description=...]
task close <id>
task thread <id> --message=... [--type=quote|info|warning]
task scan
Resolve dependencies, surface overdue/stale/auto-* changes

Capture commands

capture "the thought"
Write inline text to raw/inbox/<ts>-<slug>.md (next compile distils it)
capture --file=PATH
Capture a file's contents into raw/inbox/
capture --url=URL
Fetch a URL, strip HTML noise (<script>/<style>/<head>), store with source: url:<url> in frontmatter
capture --stdin
Read content from stdin (e.g. \`pbpaste | ${CLI_COMMAND} capture --stdin\`)
capture ... --kind=feedback
Append to raw/user/feedback.md instead of inbox/ (corrections/preferences)
capture ... --title=X --label=Y
Optional metadata (slug source + frontmatter label)

Hook commands (internal β€” wired into Claude Code hooks; safe to run manually for testing)

session-capture --mode=session-end|pre-compact --hook-protocol=claude
Read hook JSON from stdin and append the transcript to raw/sessions/.
session-capture --mode=... --transcript=PATH --cwd=PATH --session-id=X
Plain-CLI mode β€” same logic without the hook envelope. Useful for testing.
session-capture ... --format=claude (default)
Transcript-format adapter (claude, codex).
session-start [--hook-protocol=claude|codex]
Emit dynamic SessionStart context. Without the flag, prints the structured result for testing.
session-start|session-capture ... --home=PATH
Pin the agent home from the command line (how the per-home Codex hooks name it)
guard [--hook-protocol=claude|codex]
PreToolUse hook: read the tool call from stdin and exit 2 when a shell command would write a home tree (knowledge/, projects/, reports/) relative to a cwd outside the home, move the session anywhere but back to the home (claude only: a cd carries over there), find scratch in the shared temp dir by pattern or a hand-picked $TMPDIR name, rewrite git history (commit --amend, an ours merge, stash --keep-index), or commit, merge or push after a gate joined by anything but &&

Knowledge commands

knowledge lint [--fix]
Structural health check; --fix rewrites stale wikilinks + inserts backlinks
seed scan
Detect what this home could seed a teammate with (read-only JSON)
seed export --include=p1,p2 --name=AGENT [--out=PATH]
Build a seed bundle zip from home-relative paths (no review gate here β€” you are the gate)
seed import <bundlePath> [--overwrite] [--dry-run]
Overlay a bundle onto THIS home; --dry-run prints the plan + conflicts first

Slack commands (read-only; per-operator OAuth)

slack auth
One-time OAuth (PKCE) β€” opens browser, mints + persists user token
slack whoami
Show authenticated Slack identity
slack list-channels
List channels you're a member of (name, id, topic)
slack history <channel> [--since=24h] [--limit=100]
slack batch-history <ch1,ch2,...> [--since=24h] [--limit=100]
Multi-channel history in one process
slack thread <channel> <thread_ts>
slack search <query> [--in=<channel>] [--since=7d]
Categorisation lives in <HOME>/knowledge/concepts/slack-channels.md β€” read by the
/${PLUGIN}:slack skill for multi-channel composition.

Compile commands

compile status
Show queue (pending sessions, feedback, inbox)
compile next
Print next work item (no synthesis β€” run /${PLUGIN}:knowledge-compile for that)
compile write <itemId>
Mark item complete (advanced β€” synthesis writes use this internally)

Worktree commands

worktree <repoPath> --branch=BRANCH [--base=REF] [--slug=SLUG] [--extra=sub1,sub2]
Create <repoPath>-<slug> as a sibling of the main checkout, copy gitignored locals, install, build. A bare --branch is namespaced under the operator (<operator>/<name>). --base picks the start-point (default: dev β†’ develop β†’ main β†’ master β†’ current HEAD). --extra lists relative subdirs with their own lockfile. NOTE: blocked by the Bash sandbox when run from inside Claude Code (git can't write .git/config) β€” use the setup_worktree MCP tool there; this CLI is for a real terminal.
worktree list <repoPath>
Audit every registered worktree: branch, dirty/unpushed counts, ahead/behind and merge state vs the base ref, last-commit age, and a verdict (deletable / uncommitted / unpushed / pushed-unmerged / missing / base / main). Read-only β€” fine anywhere.
worktree remove <worktreePath> [--delete-branch] [--force] [--dry-run]
Safely remove a worktree: refuses on a dev/develop/main/master worktree and on uncommitted changes; needs --force when the branch has committed-but-unpushed commits; runs the repo's \`clean\` script first. Keeps the branch unless --delete-branch. --dry-run reports the status without touching anything. Same sandbox note β€” use remove_worktree there.

Sidebar commands for cmux (this CLI's, not the cmux app's own; run them from a terminal inside cmux)

cmux sidebar install
Add this home to the AgentLayer sidebar (starting it if it's the first), have cmux check it, and show it
cmux sidebar refresh
Put this home's latest projects and tasks into the sidebar (every dashboard refresh also does this)
cmux sidebar remove
Take this home out of the sidebar; the last home out deletes it
cmux sidebar order <agent>…
Put these agents first on the sidebar, in this order (by name or home folder); it holds across every home's refresh
cmux settings --file=<ghostty|cmux> [--launcher=<claude|agent>] [--json]
Compare a Mac's Ghostty or cmux settings with the recommended ones (read-only; prints what to paste and the command to run; without --json, exit 3 unless the file is complete)

Proposals commands

proposals list [--json]
What's showing, the room for more, and the heartbeat's interval
proposals decide <start|later|skip> <id>
Start it (a fresh session runs its prompt), put it off until morning, or drop it
proposals heartbeat --owner=<token> [--every=<duration>]
Make the session holding that token the heartbeat (/heartbeat passes its own), looking every 55m unless set (15m, 2h); --release ends it if that token still holds it; --off for none

Database commands

database list
List configured AGENT_DB_<NAME> connections (name + host/db, never credentials)
database schema --connection=NAME [--table=T] [--schema=S] [--database=DB]
List user tables, or describe one table's columns (read-only)
database query --connection=NAME --sql="SELECT ..." [--database=DB] [--timeout=MS]
Run read-only SQL (server-enforced READ ONLY tx; writes/DDL rejected)
database fork [--connection=NAME] [--source=DB] [--fork=NAME] [--cwd=PATH] [--repoint-env] [--env-var=DATABASE_URL] [--force] [--terminate-source] [--drop]
Clone a LOCAL database via CREATE DATABASE ... TEMPLATE. Fork name defaults to <source>_<git-branch> when --cwd is a repo, else <source>_fork. --repoint-env writes a .env.local override in --cwd; --drop tears the fork down. Remote hosts refused.

Environment

AGENT_HOME=<path>
Override agent home (default: cwd)
AGENT_PROJECTS=<path>
Override projects/ location (default: <HOME>/projects)
AGENT_KNOWLEDGE=<path>
Override knowledge/ location (default: <HOME>/knowledge)
AGENT_TIMEZONE=<tz>
Override timezone (default: system tz)

Examples

${CLI_COMMAND} capture "remember to follow up with the accountant on the annual filing"
${CLI_COMMAND} capture --file=~/notes/board-meeting.md --title="Board meeting 2026-05-28"
${CLI_COMMAND} capture --url=https://docs.anthropic.com/en/docs/claude-code/overview
pbpaste | ${CLI_COMMAND} capture --stdin --title="Clipped article"
${CLI_COMMAND} capture --kind=feedback "don't propose git push for local-only repos"
${CLI_COMMAND} task query --status=active
${CLI_COMMAND} task create --project=blog-dev --title="Draft launch post" --description="..." --priority=P1
${CLI_COMMAND} dashboard
${CLI_COMMAND} worktree /path/to/repo --branch=feat/my-thing
${CLI_COMMAND} knowledge lint --fix
${CLI_COMMAND} compile status
${CLI_COMMAND} database list
${CLI_COMMAND} database query --connection=app --sql="select count(*) from users"
${CLI_COMMAND} database fork --connection=app --cwd=/path/to/worktree --repoint-env
In-process hooks for interactive Claude Code 2.1.314 or newer. Codex and claude -p run without them: the CLI covers the commands and the session banner carries the notices. Not seen loading on this machine yet.
Instant commands
Capture a thought, log a lesson, see today or copy this conversation's session id, answered at once without a model turn.
slash commands Β· the Today and Session rows above the prompt
/capture <text>/lesson <text>/today/session
Tasks
Look up a task by id as a card, close or cancel it, and see every task id in a reply as a link that opens its file.
slash command Β· a task card above the prompt Β· links in replies
/task <id> [done|cancel]
Repo manuals
The first file read or written in a granted code repo, or named by absolute path in a shell command, attaches that repo's CLAUDE.md or AGENTS.md, once, and again after a compaction or /clear.
tool results Β· a πŸ“Ž line above the prompt
/manuals
Session reports
The reports this conversation wrote or edited, its own and its subagents', its project documents and anything attached by hand, until dismissed; a report with an HTML page shows the page.
slash command Β· a πŸ“Ž row above the prompt
/reports [attach <path>…]
Sync progress
Sync's step, elapsed time and what it is clearing, live while it runs; its report quotes counted numbers instead of a tally.
above the prompt
sync_stats
Notices
The top upgrade or sync nudge, with a button that runs it and one that snoozes it until tomorrow; also the Tab suggestion.
above the prompt Β· toast for an alert
Queue a prompt
Line up prompts while a task runs; each goes out as its own turn once the one before it ends, never mid-task.
slash command · a ⏳ count above the prompt
/queue <prompt> | clear
Proposals and the heartbeat
Start, put off or skip the sessions the agent proposes, and make one long session the heartbeat that keeps proposals coming, with no model turn for either.
slash commands Β· the heartbeat wakes on its own clock
/proposal <start|later|skip> <id>/heartbeat [15m | 2h | off | now | status]
Setup prompt
In a folder that isn't an agent home yet, a row with a button that runs init; also the Tab suggestion.
above the prompt
Agent rows
Each subagent's row shows its name, what it's doing, and a bar for how much of its context it has used.
the agent rows under the prompt, in the terminal
SessionStartFires when a session starts. Injects today’s date, the tail of your last session, today’s reports, the reports you pinned, recent git activity, and a warning when the home needs an upgrade or a fix β€” so Ace wakes up with continuity instead of a blank slate.cli.ts session-start --hook-protocol=claude
SessionEndFires when a session ends. Captures the full transcript to knowledge/raw/sessions/YYYY-MM-DD.md. This is how every session is saved β€” later compiled into long-term memory.cli.ts session-capture --mode=session-end
PreCompactFires just before Claude Code compacts (summarises) a long conversation. Captures the session up to that point so the part being compressed away is still preserved on disk.cli.ts session-capture --mode=pre-compact
PreToolUsecli.ts guard --hook-protocol=claude

Alex Chen πŸ‘€

Who Ace is working for β€” compiled from every session.

Alex Chen
America/New_York
Co-founder and CTO of Acme, a B2B logistics SaaS scaling past launch. Previously staff engineer at two startups through Series B. Writes Go and TypeScript; reviews everything touching billing.

Role

  • Owns platform, billing, and the SOC 2 track.
  • Runs the Monday planning review and the weekly launch standup.

Working Hours

  • 10:00-19:00 ET. The deep-work block before noon is sacred: no meetings, no pings.

Signal Topics

  • Agentic coding tools and review workflows.
  • Usage-based billing and revenue recognition.
  • Logistics software and freight tech.

Go deeper3 facets

preferenceslead with the number, deep work before noon104 B
profilerole, background, working hours637 B
skillsGo, TypeScript, Postgres, billing and logistics systems138 B

Ace πŸ€–

Your life co-pilot β€” who he is and how he runs.

Ace
Company agent (agent-acme, forked from agentlayer)
Sharp but approachable. Gets things done. Knows the codebase and the company.

Ace is Acme's private company agent. It pairs with engineering on real tickets, compiles the company's knowledge into a living brain, and briefs leadership every morning. Self-hosted on Acme infrastructure; nothing leaves the building.

Core Rolefrom IDENTITY.md

  • Agentic engineering: coding, debugging, monitoring, and planning with full company context.
  • Company brain: capture, compile, and serve institutional knowledge.
  • Daily briefings, task tracking, and incident support.

Vibefrom SOUL.md

  • You are Ace, Acme's company agent. Sharp, direct, allergic to fluff. You ship with the engineering team daily and brief the leadership floor every morning. Clever over polite; useful over impressive.

Operational Patternfrom IDENTITY.md

  • Briefings. The morning brief carries priorities plus signal-topic and industry news; the evening wrap is a today-only delta.
  • Code. The engineer skill for platform work and teammates' PRs.
  • Review loop. Ace implements; a second model reviews on one dossier, and Ace verifies every finding against the code.

Writing Stylefrom SOUL.md

  • Lead with the number. Tables and before/after blocks over paragraphs.
  • ASCII diagrams in chat; Mermaid in files.

Core Truthsfrom SOUL.md

  • Do the thing. Explain after, not before.
  • Verify before you claim. A number gets a source or it stays out.
  • Have a spine. Recommend once, then build to the call.
  • Figure it out. Read the file, check the context, then ask.

Boundariesfrom SOUL.md

  • Customer data stays inside Acme systems.
  • When in doubt, ask before acting externally.

Files

Ace's character and role β€” edit these to evolve them.SOUL.md Β· IDENTITY.md

Runtime

versionv1.0.9
pluginagentlayer@agentlayer
marketplaceagentlayer (github)
plugin path/home/alex/.claude/plugins/marketplaces/agentlayer
home~/agent-acme
timezoneAmerica/New_York
historymanaged by your own git setup

System

The machinery β€” settings, logs, releases.

Settings layers3 allow Β· 1 deny total

Plugin

pluginagentlayer@agentlayer
marketplaceagentlayer (github)
plugins enabledskill-creator Β· typescript-lsp Β· agentlayer

Environment4 vars

keyvaluescope
AGENT_HOMEThe agent home directory β€” the root of the knowledge tree, projects, and reports. The MCP server resolves every path from here. Defaults to the directory you launch Claude from; set it in ~/.claude/settings.json only on a machine with exactly one agent home, since a machine-wide value points every agent at the same home.~/agent-acmeuser
DISABLE_TELEMETRYNo usage metrics to Anthropic (they never carry code, prompts or file paths). Also turns off feature flags, so auto mode needs an explicit defaultMode.1user
AGENT_HOME_TIMEZONEAmerica/New_Yorkworkspace
AGENT_CODE_PATHAbsolute path to your primary codebase. Used by the setup-worktree skill and exposed as $AGENT_CODE_PATH.~/acme/platformworkspace

Secrets0 set Β· values never shown

No secrets configured. Add keys to .state/secrets/.env (loaded at boot, never displayed).

Health

file~/agent-acme/.state/logs/app.log (206 B)
today1 warn Β· 0 err
all-time1 warn Β· 0 err

Tail145 B

2026-11-21T06:31:47.930Z INFO [πŸ€– system] [cli] dashboard
2026-11-21T06:29:47.930Z WARN [πŸ€– system] [cli] compile: one inbox item deferred
βœ“ Up to date β€” home baseline matches installed v1.0.9.

v1.0.9 Β· your baseline2026-11-21

Added

  • A band above the heartbeat's prompt: what it is doing now (looking for proposals, refreshing the
  • A brain refresh, `/agentlayer:sync brain`: sync's maintenance steps (snapshot, code, compile, lint,
  • Sessions the sidebar opens (Discuss on a task or goal, a proposal's Start, Start heartbeat) land in
  • `list_sessions.ts --brief`: one line per session (id, age, branch, topic, latest ask).

Changed

  • The heartbeat looks whether or not five proposals show. `proposal_add` takes `retire` (with an
  • After each look or refresh the heartbeat rebuilds the dashboard and the cmux sidebar.
  • The sync tracker draws a brain refresh's own nine phases under its name, keeps it out of the
  • The sidebar's Discuss sparkles are no longer dimmed.
  • To show you a file, the agent puts its absolute path in the reply, which the terminal makes a link

Fixed

  • Leaving the heartbeat's session (exit, logout, a closed tab) gives the heartbeat up, so the next
  • A proposal's publish read the last saved work model, so it could put an old tasks summary back on
  • `/heartbeat now` checks the live owner before clearing, and a refresh that fails before it stamps
  • A word typed after a `/proposal` decision is no longer taken for a workspace.

⬆ Upgrade

changeleveldetail
template/AGENTS.mdmandatoryPlatform's "Keep the live home out of harm's way" paragraph

v1.0.82026-11-21

Changed

  • The heartbeat no longer sleeps 23:00–07:00. A wake goes ahead only when another session in the
  • `/heartbeat`, with or without an interval, looks for proposals at once at any hour, then waits a
  • The cmux Manager's PROPOSED section starts folded and no card opens on its own. A closed card shows

⬆ Upgrade

changeleveldetail
depsrequired`cmux-custom-manager` moves to `f885f86` (0.4.5); run `bun install` in the

v1.0.72026-11-20

Fixed

  • `install.sh` and `install.ps1` download their steps from the release tag (`RELEASE`, `$release`)

Changed

  • The release skill bumps the setup guides' release line along with the manifests, and its docs

⬆ Upgrade

- None β€” code-only, no bun install or HOME changes.

v1.0.62026-11-20

Added

  • Proposals: sessions the agent has prepared and waits on a yes for. Start opens a fresh session that
  • `proposal_add`, the tool that adds proposals, and a `proposals` CLI group: `proposals list`,
  • The heartbeat: `/heartbeat [15m | 2h | off | now | status]` makes one long-running session the
  • The `proposals` skill is the heartbeat's wake: it looks at tasks, sync, GitHub and every proposal
  • The cmux Manager shows a PROPOSED section above Needs you, across every home on the Mac. Its
  • A Discuss icon on every task and goal in the cmux sidebar opens a session on the new `discuss`
  • A tasks-at-a-glance summary in TASKS.md, one line written by sync (and by the heartbeat once it's

Changed

  • The sidebar opens a session one way everywhere: a tab where you are, or a new workspace in the
  • The Manager's session titles take two lines, section headers line up with their cards, badges drop
  • The release skill offers a docs pass after the release: it finds the docs site beside the plugin,
  • The README's skill, playbook and tool counts are checked by a test.

Fixed

  • Task titles in the cmux Agents tab take two lines, like reports.
  • A task's project pill truncates, so an open Tasks card no longer widens the sidebar.
  • The sidebar's tasks summary is one short themed sentence, and its banner stops at three lines.

⬆ Upgrade

changeleveldetail
depsrequired`cmux-custom-manager` moves to `2a8eb8e` (0.4.4); run `bun install` in the
settingsmandatoryadd `mcp__plugin_agentlayer_agent__proposal_add` to `permissions.allow`
manualoptionalProposals need a heartbeat. In Claude Code, run `/heartbeat` in one session
manualoptionalIn the cmux sidebar, each agent on the Mac shows "needs its agent updated"

v1.0.52026-11-19

Added

  • The installer checks for Node.js before Bun, on Mac, Linux and Windows. Any Node on PATH passes,
  • The Mac guide recommends MarkEdit for the agent's notes, right after CotEditor.
  • A Default apps step in the Mac guide checks that CotEditor opens `.txt` and `.json` and MarkEdit

Changed

  • Dashboard file links open the file itself in a new tab by default, on the dashboard, the
  • The manual tells the agent to show you a file with `! open <absolute path>`, so your system's
  • The radar report is sanitized before its task and plan links go in, so the report's own app or

Fixed

  • The demo dashboard's week starts on its own Monday, not a day early when the machine's clock is

⬆ Upgrade

changeleveldetail
template/AGENTS.mdmandatoryPlatform's "Keep the live home out of harm's way" paragraph
manualoptionalDashboard links now open the file itself instead of Obsidian. To keep

v1.0.42026-11-19

Added

  • `cmux sidebar order <agent>…` puts the named agents first on the cmux sidebar, in that order
  • "Refresh my sidebar" refreshes the cmux sidebar alone in one dashboard call, with no session scan

Changed

  • The dashboard tool returns `sidebar` (`written`, `unchanged`, `not-installed`, `not-joined` or
  • The dashboard's Reports page and the sidebar's reports list sort by when a report was last
  • The sidebar keeps its agents in the order they joined instead of sorting them by folder.
  • The README leads with what the plugin is, the cmux workstation and the one-line installer.

Fixed

  • Three short-named agent chips fit beside the cmux sidebar's tab pill instead of the third

⬆ Upgrade

- None β€” code-only, no bun install or HOME changes.

v1.0.32026-11-18

Added

  • A guided installer for macOS, Linux and Windows: `curl -fsSL agentlayer.one/install.sh | bash`
  • Every agent has its own colors: a primary and an accent on a `Colors` line in IDENTITY.md, chosen
  • A home extends a plugin skill from `extensions/skills/<skill>.md`: session start lists each one,
  • A home's own report categories: `report_write` takes any kebab-case folder except `captures`,
  • The morning brief flags a red CI run on the code repo's default branch (with the GitHub pack and
  • A browser flow's target can carry its own Chromium flags, added after the shared ones.
  • The read-only `cmux settings` verb compares a Mac's Ghostty and cmux configs with the recommended

Changed

  • Homes keep their pages as files: init writes `"enableArtifact": false` to the home's
  • Codex homes default to `gpt-6.2-sol` at high effort. A user-global Codex config still on a past
  • Helpdesk's org rules come from the home's `extensions/skills/helpdesk.md` instead of a
  • Per-agent billing and `agent`: the installer's closing start line says `agent` for a home with
  • The session banner's Agent line leads with the agent's emoji.
  • A home moved in place (same folder, new plugin) reads as moved from that plugin, not copied,
  • The seed wizard on agentlayer.one is retired; a seed bundle comes from a teammate's export. A
  • The work model and the cmux sidebar entry carry the agent's colors, so both schemas move up one;

Fixed

  • Pack pickers in init and configure-skills listed up to eleven packs in one question, so packs got
  • The Windows installer names a tool by its full path when the window you started it in can't find

⬆ Upgrade

changeleveldetail
scriptrequiredrun skills/upgrade/scripts/1.0.3.ts (a Codex home whose `.codex/config.toml` sets `model = "gpt-6.1-sol"` moves to `gpt-6.2-sol`; any other model, and a home with no Codex config, is left as it is).
template/AGENTS.mdmandatorya routing row for a page or document asked for outside a skill, and `extensions/skills/` in the home's tree.
settingsmandatoryupgrade's baseline reconcile adds `"enableArtifact": false` to `settings.json` when neither home settings file sets `enableArtifact`. Applied automatically; set it to `true` to keep Artifacts.
manualoptionala home whose agent isn't Oppi shows Oppi's colors until IDENTITY.md has a `Colors` line under `## Who`. To pick a pair, ask the agent to "show me the color pairs and set mine": it shows the four with the plugin's `colors` verb and writes the line `colors --line=<choice>` prints below the `Emoji` line.
manualoptionalwith the cmux pack, every other home in the sidebar shows "needs its agent updated to show here" until that home runs `/agentlayer:upgrade` (or a dashboard refresh) on this version.
manualoptionalan organisation plugin that ships helpdesk org rules at `skills/helpdesk/references/org.md` no longer has them read: move that file's text into each home's `extensions/skills/helpdesk.md`.

v1.0.22026-11-17

Added

  • The cmux pack (macOS, cmux 0.65.2 or later): an AgentLayer panel in cmux's right sidebar that
  • `cmux sidebar install | refresh | remove` CLI verbs, and every dashboard refresh keeps the
  • init offers the Helpdesk, App Store and cmux packs with the others; cmux is ticked by default
  • A report's status shows as a word with a coloured badge, on the dashboard and in the sidebar.

Changed

  • One work model of the home's projects and tasks, read once per rebuild and kept in
  • The dashboard's Goals read like the sidebar's.
  • Outside Obsidian, the dashboard opens HTML pages as pages in a new tab.
  • The agent rows under the prompt are drawn by a mod, since Claude Code 2.1.323 removed
  • The plugin declares Claude Code 2.1.314 or later, so an older host skips it rather than

Fixed

  • Dashboard writes run one at a time, each from the files as they are, so two refreshes can't
  • The sidebar reads its file back whatever its titles hold, and keys a project's links by where

Removed

  • The plugin's `subagentStatusLine` setting and the `statusline --subagent` renderer, which

⬆ Upgrade

changeleveldetail
depsrequirednew dependency `cmux-custom-manager` (the sidebar's library); run `bun install` in the plugin root.
manualoptionalon macOS with cmux 0.65.2 or later, run `/agentlayer:configure-skills` and pick cmux to put this home in the AgentLayer sidebar.

v1.0.12026-11-16

Added

  • A moved home's first session checks the move with you before the upgrade and the sync
  • `upgrade` flags a home missing from the auto-mode "Agent homes:" entry, and a Codex-wired home
  • A new home that keeps the name Oppi gets its nickname, Ops.

Changed

  • `curl_run` accepts a listed set of request flags and one URL per call, and reads no `.curlrc`,
  • Every outbound request has a deadline and stops when its call is cancelled.
  • Codex wiring is named after the plugin: `[mcp_servers.agentlayer]`, `[permissions.agentlayer]`
  • Source layout: each domain owns its `tool.ts` and one registry imports them; only entry points,
  • The README leads with AgentLayer and introduces Oppi; the changelog notes that `agent-kevin`

Fixed

  • Security: tool paths that could write outside the home or hand out its secrets; curl's
  • Capture: the session briefing is redacted (the whole first turn, before it is cut); three ways
  • Session start: the size cap never cuts a warning, and the session tail is where the session
  • Tasks: five ways a task file lost data or a task went missing.
  • Knowledge: feedback logged mid-compile stays pending, and prune repoints the days it deletes.
  • The CLI reads the named home's settings, survives a mistyped time zone, and keeps a note that
  • A report's title, summary or extra key can't break the report or its index line.
  • Atomic rewrites keep the file's mode; `.env` files read `export` lines; one cadence writer,
  • The GitHub sweep compares "new since the last sweep" as instants, not strings.
  • Four skill scripts that wrote or matched the wrong thing.
  • A moved home's first session always syncs, even across a restart.

⬆ Upgrade

changeleveldetail
manualrequiredonly for a home wired for Codex on 1.0.0. The upgrade's `codex_setup` writes the new `agentlayer` tables but leaves the old ones: in the home's `.codex/config.toml`, delete `[mcp_servers.agent]` and `[permissions.agent]` and set `default_permissions = "agentlayer"`, then delete `.codex/rules/agent.rules`. A home without `.codex/` has nothing to do.

v1.0.02026-11-15

Added

  • Oppi, the default agent: name, octopus avatar, and "Many arms, one brain" in SOUL.
  • find-session searches the brain's session logs as well as Claude Code's transcripts, and
  • A moved home's first session says where it came from, finishes the move, remembers it in

Changed

  • The plugin is `agentlayer` and its MCP server is `agent`: commands are `/agentlayer:<skill>`
  • The package lives at the plugin root, and the CLI is `src/cli.ts`, run with `bun`; there is
  • The plugin root, its name, its version and the CLI path each come from one place.

Removed

  • Upgrade scripts and legacy names from the 0.x releases; a home arrives here through the move.

⬆ Upgrade

changeleveldetail
depsrequiredthe package moved to the plugin root; a checkout runs `bun install` there once.
template/AGENTS.mdmandatorythe bundled server is `agent`, captures go through the `capture` tool, and the CLI line names `src/cli.ts`.
template/SOUL.mdoptionala new core truth, "Many arms, one brain".
template/knowledge/concepts/audit-premise-decay.mdoptional`/agentlayer:` names (already applied by the move).
template/knowledge/concepts/karpathy-wiki.mdoptional`/agentlayer:` names (already applied by the move).
template/knowledge/concepts/markdown-native-task-management.mdoptional`/agentlayer:` names (already applied by the move).
template/knowledge/concepts/self-evolution-loop.mdoptional`/agentlayer:` names (already applied by the move).
template/rules/swift.mdoptional`/agentlayer:` names (already applied by the move).
manualoptionalfor an agent that took the name Oppi: IDENTITY's Vibe can end "An octopus at heart: many arms working at once, one brain behind them." (the upgrade never edits IDENTITY's `## Who`).

Status 🟒

All systems nominal. The sidebar badge is green only when the five blocking signals below are all zero.

0overdue tasks
0pending compiles
0log errors today
0missing imports
0unreadable tasks

Overdue tasks0

Open tasks whose due date has passed β€” read straight from each task file’s frontmatter.
βœ“Nothing past due.

Pending compiles0

Captured session days not yet absorbed into long-term memory β€” 7 day-file(s) captured vs 7 compiled. Clear it with /agentlayer:sync or /agentlayer:knowledge-compile.
βœ“Everything captured has been compiled.

Log errors0

ERROR-level lines the MCP server and hooks wrote to app.log today. Warnings don’t count.
βœ“No errors logged today.open the log tail β†’

Context importsall present

Files the .claude/CLAUDE.md @-import chain loads at session start (the AGENTS.md manual, the identity stack, the indexes) β€” a missing one means a session boots without that context.
βœ“All static imports present.

Unreadable tasks0

Task files whose frontmatter won’t parse. They are missing from every list on this dashboard and from TASKS.md β€” fix the frontmatter (it must open with `---` on line 1) and they reappear.
βœ“Every task file parses.

Going stale1 Β· informational

Tasks not closed and untouched for 7+ days. Informational only β€” it never turns the badge amber.
●1 task(s) going stalereview them β†’