session-end
Skill0 starsChanged 7 months agoMITView on GitHub
End-of-session wrap-up: update MEMORY.md with lessons learned, capture session summary with what was done and what's next, update overall plan and any active sub-plans, and prepare handoff notes for the next session. Use at the end of every work session.
- Commits and pushes
30 other projects use a version of this.
Adopted by
Most recently taken up by
- timursafiullin/aodtheir own version, first seen Nov 15, 2026
- mikkiola/radartheir own version, first seen Nov 15, 2026
- spizganed/skillstheir own version, first seen Nov 8, 2026
- edxleon/runspectortheir own version, first seen Nov 8, 2026
- salvo8519/fairmarktheir own version, first seen Nov 8, 2026
- puritysb/AgentDecktheir own version, first seen Nov 2, 2026
Used with
Projects with it also use ship.
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.
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- puritysb/AgentDeck★ 299same name
- faizkhairi/claude-code-blueprint★ 73same name
- Kanevry/session-orchestrator★ 53same name
- valpere/session-indexer★ 42same name
- namedtoaster/The-Last-Mile★ 39same name
- iamneilroberts/claude-skills★ 26same name
- IlyaGorsky/memory-toolkit★ 13same name
- edxleon/runspector★ 11same name
- mae616/ai-template★ 9same name
- freskhu/genesis★ 5same name
20 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- application-trackerSkill
- applySkill
- cold-outreachSkill
- company-deep-diveSkill
- contact-populationSkill
- job-searchSkill
- meeting-prepSkill
- onboard-userSkill
- resume-tailorSkill
- session-checkpointSkill
- session-startSkill
- warm-followupSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
If lessons found: present to user for approval before updating rules/skills.
- Distinctive: line 31
If no lessons: skip — don't force it.
- Distinctive: line 35
Update the project's MEMORY.md with:
- Distinctive: line 42
Keep MEMORY.md under 200 lines.
- Very specific: line 61
If there's an active sub-plan in plans/[date]/:
- Distinctive: line 62
Read the plan file.
- Distinctive: line 63
Update phase/step completion status (✅ for done, ⬜ for pending).
- Distinctive: line 64
Add any newly discovered blockers or decisions.
- Distinctive: line 67
If no active sub-plan, skip.
- Very specific: line 100
If multiple sessions on the same date, append a letter suffix: SESSION-SUMMARY-{user-slug}-YYYY-MM-DDb.md.
“Common” is measured: kept by at least 6 in 10 of the 23 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
Session End
Standardized session wrap-up to preserve context across sessions.
What This Skill Does
- Capture lessons learned — check if anything should be added to rules, skills, or memory.
- Update MEMORY.md — record key facts, technical details, and project state changes.
- Update plans — overall plan + any active sub-plan.
- Write session summary — what was done, what's pending, what to do next.
- Git commit + push — commit all changes and push to GitHub.
- MCP health check — note which MCPs are connected/disconnected for next session.
Workflow
Step 1: Lessons-learned check
Review the session for:
- Mistakes that could be prevented with a rule
- Repeated workflows that could become a skill
- Technical discoveries worth remembering
- Rules or skills that need updating based on what happened
If lessons found: present to user for approval before updating rules/skills. If no lessons: skip — don't force it.
Step 2: Update MEMORY.md
Update the project's MEMORY.md with:
- Any new project structure changes
- New technical details discovered
- Updated database status (table IDs, field changes)
- Tool/dependency changes
- Key decisions made this session
Keep MEMORY.md under 200 lines.
Step 3: Update plans (MANDATORY)
3a: Update overall plan (ALWAYS do this)
File: plans/OVERALL-PLAN.md (create if not present).
This is the living master plan. Update every session with:
- Last Updated date at the top
- Workstream progress — counts, milestones, completed items
- Current Priorities — adjust based on what was done and what's next
- Blockers — add new ones, remove resolved ones
- Key Metrics — update the snapshot table if numbers changed
- Session History — add a row for this session
- Next Session Checklist — concrete next steps
3b: Update active sub-plan (if any)
If there's an active sub-plan in plans/[date]/:
- Read the plan file.
- Update phase/step completion status (✅ for done, ⬜ for pending).
- Add any newly discovered blockers or decisions.
- Note the exact resumption point ("Resume at Phase X, Step Y").
If no active sub-plan, skip.
Step 4: Write session summary
Create: plans/archive/SESSION-SUMMARY-{user-slug}-YYYY-MM-DD.md
# Session Summary — {user-slug} — YYYY-MM-DD
## What Was Done
- ...
## What's Pending
- ...
## Next Session Priorities
1. ...
2. ...
3. ...
## MCP Status
- nocodb: [Connected/Disconnected]
- linkedin: [Connected/Disconnected]
- context7: [Connected/Disconnected]
- playwright: [Connected/Disconnected]
## Files Modified This Session
- ...
## Notes for Next Session
- ...If multiple sessions on the same date, append a letter suffix: SESSION-SUMMARY-{user-slug}-YYYY-MM-DDb.md.
Step 5: File-state check + git sync
This project IS a git repo. The remote is whatever you configured during setup (typically a fork of <your-org>/job-hunt-os).
git add -A
git status --short
git commit -m "Session $(date +%Y-%m-%d): <brief summary>"
# Push using whatever auth your environment has configured.
# If using PAT-in-URL pattern (documented in docs/SETUP.md):
# 1. Set remote with PAT
# 2. Push
# 3. Strip PAT from remote (ALWAYS — even if push fails)
git push origin mainReport: "Git: committed N files, pushed to origin/main" or "Git: push failed — [error]".
List key files created/modified during the session in the session summary under "Files Modified This Session".
Step 6: Confirm ready
Tell the user: "Session wrapped up. You can restart Claude Code — the next session will pick up from MEMORY.md, the overall plan, and the session summary."
Rules
- NEVER skip MEMORY.md update — it's loaded into every session's context.
- NEVER skip overall plan update — it's the master tracker across all sessions.
- Keep MEMORY.md concise — under 200 lines, link to other files for details.
- Don't create lessons that don't exist — if nothing was learned, say so.
- Ask before updating rules/skills — present proposed changes for approval.
- Always note MCP status — saves debugging time in the next session.
- Always update active sub-plan — if a multi-session plan is in progress, update its status.
- ALWAYS git commit + push at session end — the repo is the shared source of truth.
- NEVER leave a PAT in the remote URL — strip it after every push, even on failure.
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.

