Session close checklist: tests, final commit, clean state and a summary for the next session.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Session end
## Steps (in order)
1. **Full tests** with the command declared in `AGENTS.md` → green.
2. **Final commit** if changes remain: conventional commit + role byline.
3. **Push** the working branch.
4. **Clean state**: `git status` without pending changes (or only inside the feature worktree).
5. **Summary**: what was done, what remains, relevant files.
## Checklist
- [ ] Tests green
- [ ] Incremental commits (not one giant commit)
- [ ] Role byline on agent commits
- [ ] No open QA or review findings
- [ ] Default branch clean; work lives in its branch/worktree
- [ ] Summary written for the next session
## Persistent memory (if configured)
Store the session summary with the project's memory tool. If there is no memory configured, the
summary goes to the chat and to the commit or PR description.
The line at the top of this page pins the label git:20261021.0f705f1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_263dqzpnwgwme4gs
GET https://markdownregistry.com/api/v1/resolve?ref=cedaniel200/atlas-template/session-end
GET https://markdownregistry.com/api/v1/blob/fd292c25b4e4fcee8a2b884bdb5a54c131b3af1319559346230048a0bbee3f51
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
cedaniel200/atlas-template · .agents/skills/conventional-commits/SKILL.md · Use for ALL commits — enforces incremental commits with Conventional Commits prefixes and descriptive messages in the…
cedaniel200/atlas-template · .agents/skills/gherkin-specs/SKILL.md · Use when writing or editing OpenSpec specs — guides Gherkin-style GIVEN/WHEN/THEN scenarios in the domain's business…
cedaniel200/atlas-template · .agents/skills/grilling/SKILL.md · Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or…
cedaniel200/atlas-template · .agents/skills/openspec-apply-change/SKILL.md · Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or…
cedaniel200/atlas-template · .agents/skills/openspec-archive-change/SKILL.md · Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after…
cedaniel200/atlas-template · .agents/skills/openspec-explore/SKILL.md · Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use…
cedaniel200/atlas-template · .agents/skills/openspec-propose/SKILL.md · Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they…
cedaniel200/atlas-template · .agents/skills/openspec-sync-specs/SKILL.md · Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta…
kanevry/session-orchestrator · .codex-plugin/skills/session-end/SKILL.md · Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates…
kanevry/session-orchestrator · .agents/skills/session-end/SKILL.md · Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates…
kanevry/session-orchestrator · .cursor/skills/session-end/SKILL.md · Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates…
kanevry/session-orchestrator · skills/session-end/SKILL.md · Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates…
namedtoaster/the-last-mile · skills/session-end/SKILL.md · Wrap up a working session automatically. Runs the project's checks, adds manual test items to the release checklist…
lstr-1/skills · sex/skills/session-end/SKILL.md · Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates…
lstr-1/skills · orchestrator/skills/session-end/SKILL.md · Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates…
