status
Skill0 starsChanged 5 months agoMITView on GitHub
One read-only dashboard for "what's going on in this project": active sessions (who's working where), the plan board (every plan by status with progress), and deploy state (what's live vs what's merged and waiting). Use when asked "what's in flight", "what's the status", "who's working on what", "what's waiting to deploy", or at the start of a session in a busy repo. Never mutates anything — repairs belong to /soloship:cleanup.
177 other projects use a version of this.
Adopted by
Most recently taken up by
- zaynram/scholartheir own version, first seen Nov 8, 2026
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- leinardi/adversarial-review-looptheir own version, first seen Nov 8, 2026
- emotixco/claude-skills-foundertheir own version, first seen Nov 8, 2026
- flung-official/flung-claude-plugintheir own version, first seen Nov 8, 2026
Used with
Projects with it also use off, list and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
StakeholderSenseiSkilloff
Disable polygraph for this repo (user-only escape hatch; all hooks no-op)
Also in 4 projects that use this
SuShuhengSkilllist
Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.
Also in 8 projects that use this
kennethleungtySkillpause
Pause — stop the music (alias for /stop)
Also in 6 projects that use this
codebycoreySkillnew
Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.
Also in 7 projects that use this
michaelenglandSkillimport
This skill should be used when the user wants to import an existing .pptx file into deckwright, bring in a PowerPoint that was created outside this tool, reverse-engineer a presentation for editing, or invoke /deckwright:import. Converts a .pptx into a PptxGenJS generation script so it can be edited and regenerated through the deckwright pipeline.
Also in 5 projects that use this
genomewalkerSkillresume
Resume a thread by loading its ~800-token context capsule
Also in 15 projects that use this
Other versions177 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 177
- anthropics/claude-for-legal★ 9.5ksame name
- microsoft/TokenEconomizer★ 5ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- H-mmer/pentest-agents★ 815same name
- emotixco/claude-skills-founder★ 796same name
- me2resh/apexyard★ 542same name
- dsifry/metaswarm★ 426same name
- ffroliva/gflow-cli★ 367same name
- serithemage/serverless-openclaw★ 196same name
167 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- src/AGENTS.mdAGENTS.md
- .cursor/rules/publish-version-bump.mdcCursor rule
- .cursor/rules/release-version-sync.mdcCursor rule
- antigravitySkill
- auditSkill
- autoplanSkill
- bootstrapSkill
- brainstormSkill
- browseSkill
- ceo-reviewSkill
- clarifySkill
- cleanupSkill
- code-reviewSkill
- codexSkill
- component-inventorySkill
- context-restoreSkill
- context-saveSkill
- critiqueSkill
- cronSkill
- csoSkill
- cursorSkill
- debugSkill
- deepen-planSkill
- design-reviewSkill
- devex-reviewSkill
- document-reviewSkill
- eng-reviewSkill
- executing-plansSkill
- fableSkill
- finishSkill
- frontend-designSkill
- grill-meSkill
- grokSkill
- implementSkill
- learnSkill
- office-hoursSkill
- onboardSkill
- plan-design-reviewSkill
- planSkill
- polishSkill
- qaSkill
- reviewSkill
- shipfastSkill
- shipthoroughSkill
- simplifySkill
- specSkill
- subagent-driven-developmentSkill
- test-driven-developmentSkill
- ui-auditSkill
- ui-ux-pro-maxSkill
- using-git-worktreesSkill
- verification-before-completionSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 146 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
If you are running this skill in Codex, read ../references/codex-compatibility.md before following host-specific tool instructions.
- Distinctive: line 24
All live state comes from the shared coordination dir (the break-room whiteboard every worktree of this repo can see):
- Very specific: line 33
If COORD doesn't exist yet, say so ("no session coordination state yet — it appears after the first Claude session with Soloship hooks …
- Very specific: line 47
Read dir and branch from each file.
- Very specific: line 61
Soft flag — main-checkout session with worktrees active: if any session's location is "main checkout" while other worktrees exist, append …
- Distinctive: line 137
Never mutate: No pruning, no frontmatter fixes, no lock clearing, no tag operations (git fetch --tags is the only network call, and it only …
- Distinctive: line 141
If nothing is in flight anywhere: say exactly that in one line per section.
“Common” is measured: kept by at least 6 in 10 of the 146 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Host Compatibility
If you are running this skill in Codex, read ../references/codex-compatibility.md before following host-specific tool instructions. Claude Code should continue to use the Claude-specific tools and command wrappers described here.
Soloship Status
One glance that answers "what's going on in this project" — without probing
git logs, without running the heavyweight /cleanup. Strictly read-only:
this skill never fixes, prunes, or rewrites anything. When it spots something
wrong, it says so and points at /soloship:cleanup (the reconciler) or the
responsible skill.
All live state comes from the shared coordination dir (the break-room whiteboard every worktree of this repo can see):
COORD="$(cd "$(git rev-parse --git-common-dir)" && pwd -P)/soloship"
# thresholds (defaults if config.json absent: active 15, idle 60, lock stale 45)
cat "$COORD/config.json" 2>/dev/nullIf COORD doesn't exist yet, say so ("no session coordination state yet — it
appears after the first Claude session with Soloship hooks installed") and
still render Sections 2 and 3, which only need the filesystem and git.
Section 1: Sessions
For each $COORD/sessions/*.json, compute heartbeat age from the file's
mtime and classify with the config thresholds:
- active — heartbeat younger than
session_active_min - idle — younger than
session_idle_min - presumed dead — older than that (SessionStart prunes files older than
session_prune_hours; do NOT delete anything here)
Read dir and branch from each file; label the location "main checkout" or
"worktree <basename>". Overlay claims: if a $COORD/claims/*.json names this
session_id, show which plan it's implementing.
SESSIONS
● this session main checkout, main
● worktree feat-x on feat-x — implementing 2026-07-05-feature-x-plan.md (heartbeat 2 min ago)
○ worktree fix-y on fix-y — idle 34 min
✝ 1 presumed-dead session file (no heartbeat for 3h) — /soloship:cleanup prunes theseMark which one is the current session (its pid equals this shell's $PPID).
Soft flag — main-checkout session with worktrees active: if any session's
location is "main checkout" while other worktrees exist, append
(!) authoring in the main checkout while N worktrees are active to its line.
The main checkout is the contested directory every session shares; work
belongs in worktrees, landed via references/merge-sequence.md. Informational
only — never block, never mutate.
Section 2: Plan Board
List every docs/plans/*.md (excluding archive/), read each frontmatter,
and group by status using the unified vocabulary (see the plan skill's
Artifact Contract). Apply the legacy mapping when rendering old plans:
Not started → planned, active → in-progress, completed → done. Statuses
outside both vocabularies (proposed, Implemented, missing frontmatter, …)
render in an unknown — needs triage group with their literal value; map
the obvious ones by meaning (e.g. Implemented reads as done) but say you
did. /soloship:cleanup normalizes them.
Live claims overlay frontmatter. Frontmatter edited inside a worktree
branch isn't visible in other checkouts until merge, so for in-flight work the
claim files are the real-time truth and frontmatter is the durable record that
catches up on merge: a plan with a live claim renders as in-progress
(claimed) even if the frontmatter here still says planned.
PLAN BOARD
in-progress
2026-07-05-feature-x-plan.md 2/5 · session worktree feat-x · branch feat-x · updated today
planned
2026-05-18-deploy-autorollback… planned 49 days ago, never started
backlog (2) · blocked (0) · done (12, archived) · abandoned (1)Cheap disagreement flags only (no deep git analysis — that's /cleanup):
- status
done/abandonedbut file still outsidearchive/→ note the lifecycle action pending - status
in-progresswith no live claim and no fresh heartbeat → "may be stale — /soloship:cleanup reconciles" - claim file whose session is presumed dead → "orphaned claim — /soloship:cleanup clears it"
- freshness (ttl_days) warnings for
planned/in-progressonly;backlog,done,abandonedare exempt.
Section 3: Deploy State
git fetch --tags origin 2>/dev/null # read-only against the working tree; skip silently if offline
# Targets: every prod* tag (multi-target repos use prod-<target>; also honor soloship-prod)
git tag -l "prod*" "soloship-prod*"
# Per tag: what's live, and what's merged-but-undeployed
git log -1 --format="%h %ad %s" --date=relative <tag>
git log <tag>..origin/main --onelineAlso check the deploy lock: $COORD/deploy.lock — holder session, age vs
deploy_lock_stale_min.
DEPLOY
prod → 3f2c1a9 "fix: rate limiter" (deployed 2 days ago)
waiting on main: 4 merged, undeployed changes
a1b2c3 feat: session presence
…
deploy lock: not held (or: HELD by worktree feat-x, 12 min — fresh, a deploy is running)- No
prod*tag at all → "no tracked deploys yet — the first production deploy through /soloship:shipfast or /soloship:shipthorough creates the prod tag." - Lock held and older than
deploy_lock_stale_min→ "presumed stale — only the user may clear it (the deploy sequence explains how)."
Output Rules
- Plain English, compact — the three sections above and nothing else. It should read in ten seconds.
- Relative times ("2 min ago", "49 days"), not raw timestamps.
- Never mutate. No pruning, no frontmatter fixes, no lock clearing, no
tag operations (
git fetch --tagsis the only network call, and it only updates refs). Every problem gets a one-line pointer to the fixing command instead. - If nothing is in flight anywhere: say exactly that in one line per section.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

