close
Skill0 starsChanged 3 months agoMITView on GitHub
Reconcile authoritative run evidence and issues into a truthful terminal status, limitations and portable handoff. Use when a lifecycle run must end as complete, failed, cancelled or explicitly handed off with all evidence and open issues reconciled.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- matthewwong525/WongStacktheir own version, first seen Nov 8, 2026
- vzhukovs/podman-desktop-kittheir own version, first seen Nov 1, 2026
- sophonfinance-wq/finance-automation-portfoliotheir own version, first seen Nov 1, 2026
- PapiScholz/session-closuretheir own version, first seen Oct 17, 2026
- GusevV1987/ai-workspace-kittheir own version, first seen Oct 15, 2026
- charly-vibes/incitacionestheir own version, first seen Oct 14, 2026
Used with
Projects with it also use open, reconcile and 7 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.
BlockSkillopen
Open markdown documents in Penpal for collaborative review. Use when you want a human to review a document, plan, or research artifact.
Also in 5 projects that use this
howellsSkillreconcile
Audit a project against current plugin conventions and offer to update structure.
Also in 3 projects that use this
Microsoft AzureSkillvalidate
Run the full CI validation workflow locally before submitting a PR. Use this as a final check to ensure all Azure DevOps CI pipeline steps will pass.
Also in 4 projects that use this
AnthropicSkillstart
Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
Also in 6 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 8 projects that use this
OpenAISkillbootstrap
Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.
Also in 3 projects that use this
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- Kanevry/session-orchestrator★ 53same name
- wrg32786/aigent-os★ 25same name
- sophonfinance-wq/finance-automation-portfolio★ 16same name
- maxwellsdm1867/wheeler★ 12same name
- matteo-stratega/claude-cortex★ 8same name
- matthewwong525/WongStack★ 7same name
- snapsynapse/skill-provenance★ 7same name
- BriGadja/iapreneurs-claude-code-kit★ 6same name
- Magnus-Gille/claude-skills★ 5same name
- apideck-libraries/api-skills★ 4same name
16 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 repository30 other files it gives its agents.
- auditSkill
- bootstrap-agent-contextSkill
- buildSkill
- decision-logSkill
- feature-trackerSkill
- handoffSkill
- health-checkSkill
- idea-to-briefSkill
- live-state-preflightSkill
- portfolio-reviewSkill
- pre-commit-reviewSkill
- resolveSkill
- retrospectiveSkill
- session-summarySkill
- spec-packSkill
- stack-summarySkill
- strategizeSkill
- testSkill
- the-loop-autonomySkill
- the-loop-autoSkill
- the-loop-cloudSkill
- the-loop-controlSkill
- the-loop-doctorSkill
- the-loop-endlessSkill
- the-loop-parallelSkill
- the-loop-setupSkill
- the-loop-skill-creatorSkill
- the-loopSkill
- the-loop-skill-plannerSkill
- the-loop-watchSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Use after Test reports the done gate satisfied, or when a mission must stop as blocked, failed, cancelled, waiting or kill-halted with its …
- Very specific: line 46
run ID, stage close, track, declared asset and objective.
“Common” is measured: kept by at least 6 in 10 of the 21 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
Close
Purpose
Provide the complete bundled fallback for lifecycle.close. End one bounded mission with a truthful status and portable handoff based on authoritative evidence rather than the worker narrative.
Use when
Use after Test reports the done gate satisfied, or when a mission must stop as blocked, failed, cancelled, waiting or kill-halted with its current truth preserved.
Required inputs
- Validated run ID, declared asset, track, objective, done gate and current stage.
- Authoritative event head, projected run and lease, pending-operation state and authority record.
- Complete route, evidence and issue references for the mission.
- Delivered artifacts, current source or repository state and usage against budgets.
- Required terminal decision and any explicit cancellation or recovery authority.
Reject summaries that conflict with the event chain or issue ledger.
Procedure
- Validate the authoritative chain and derive the current run, lease and pending-operation state.
- Compare every done-gate condition with current persisted evidence.
- Validate that
open_blocking_issuesequals the ledger count and inspect every open blocking issue. - Preserve all failed, blocked, denied, unverified and unknown outcomes in the digest.
- Confirm delivered artifacts, route history, authority used, budgets and last completed action.
- Emit
completeonly when every required evidence item passed and no open blocking issue remains. - Otherwise emit the exact valid status and terminal reason; never convert an incomplete mission to complete.
- Produce a portable handoff with reproduction steps and the next safe action for every unresolved item.
Output contract
Return:
- run ID, stage
close, track, declared asset and objective; - delivered artifacts and source or repository state;
- route, evidence and issue outcomes;
- authority used, lease and usage summary;
- last completed action, pending or unknown effects and unresolved gates;
- exact final status, terminal reason and portable handoff.
Evidence gate
COMPLETE requires all done-gate evidence passed and zero blocking issues outside closed. Any missing, stale, failed, blocked, denied or unverified required evidence blocks completion. The final event must satisfy the run-state contract.
Track requirements
For the code track, preserve revision or worktree state, reproducible checks and deployment or release status. For the non-code track, preserve final artifact, sources, factuality and review evidence plus publication status. Both code track and non-code track distinguish produced from externally published.
Safety and authority
Close cannot repair state by assertion, replay an unknown effect or perform an unapproved outward action. Elevated authority remains visibly warned. Kill-halted, waiting, failed and cancelled states stay truthful and require their defined recovery path.
Self-refutation
Compare the final claim with authoritative evidence and the issue ledger. Ask whether any missing check, unresolved effect, open blocker or stale input contradicts the proposed status.
Halt conditions
Halt completion when the event chain is invalid, evidence cannot be resolved, the blocking count drifts, a pending outcome is unknown, authority is absent for the terminal event, the namespace changes or a stop signal requires halted_kill_switch. Still return the last verified state and next safe action.
Core execution does not require network access or the source checkout. The links below are optional public documentation.
References
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.

