finalize
Skill67 starsChanged 4 months agoMITView on GitHub
End-of-session COMP update — record decisions, progress, and state changes
22 other projects use a version of this.
Adopted by
Most recently taken up by
- PL-Coding-GmbH/Skillstheir own version, first seen Nov 8, 2026
- DnsQueen/orcinus-skillstheir own version, first seen Nov 8, 2026
- MagicJosh/rastheir own version, first seen Nov 2, 2026
- SDSLeon/lightcodetheir own version, first seen Nov 1, 2026
- Porabuild/Poracodetheir own version, first seen Nov 1, 2026
- nrflo/nrflotheir own version, first seen Oct 29, 2026
Used with
Projects with it also use simplify, commit and 1 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.
Hugging FaceSkillsimplify
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Also in 3 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- morethanwords/tweb★ 2.7ksame name
- educlopez/ui-craft★ 441same name
- zifeo/lade★ 135same name
- Porabuild/Poracode★ 121same name
- SDSLeon/lightcode★ 121same name
- redis/docs★ 86same name
- skillberry-ai/cap-evolve★ 69same name
- PL-Coding-GmbH/Skills★ 18same name
- alexiolan/craft-skills★ 17same name
- grimoire-rs/grimoire★ 15same name
12 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 repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autoresearchSkill
- brainstormSkill
- bug-huntSkill
- check-resolvableSkill
- compSkill
- debugSkill
- dialectic-reviewSkill
- distillSkill
- implementSkill
- learnSkill
- plan-taskSkill
- premortemSkill
- red-teamSkill
- researchSkill
- retroSkill
- reviewSkill
- rsbSkill
- sessionsSkill
- shipSkill
- socratesSkill
- tradeoffSkill
- verifySkill
- wrapupSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 10 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
10
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 11
Update the COMP files for the current project to capture this session's work.
- Very specific: line 15
If $ARGUMENTS specifies a project, use that directory.
- Distinctive: line 32
Keep under 20 lines — this is a session-scoped snapshot, not a log
- Distinctive: line 36
Add new items if scope changed
- Distinctive: line 37
Update "current phase" or "next steps" sections
- Distinctive: line 41
Add or update entries for:
- Distinctive: line 46
Do NOT duplicate information already in CLAUDE.md.
- Distinctive: line 67
Read each COMP file before editing it
- Distinctive: line 68
Don't duplicate information across COMP files
- Distinctive: line 69
Keep entries concise — future sessions need scannable notes, not essays
- Distinctive: line 70
If nothing meaningful happened this session, say so rather than adding noise
“Common” is measured: kept by at least 6 in 10 of the 22 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 Finalization
Update the COMP files for the current project to capture this session's work.
Determine Scope
If $ARGUMENTS specifies a project, use that directory. Otherwise, infer from the current working directory and conversation context. If unclear, ask.
Process
Step 1: Summarize the Session
Review the conversation to identify:
- What was accomplished
- What decisions were made (and why)
- What files were created, modified, or deleted
- What's left to do
- Any gotchas or surprises discovered
Step 2: Update PLAN.md — Current State Section
Refresh the ## Current State section at the top of PLAN.md:
- What's in flight right now (current step, active branches, open questions)
- Known broken things, blockers
- What to do next session
- Keep under 20 lines — this is a session-scoped snapshot, not a log
Also update the rest of PLAN.md:
- Mark completed items as done
- Add new items if scope changed
- Update "current phase" or "next steps" sections
- Note any blockers
Step 3: Update MEMORY.md
Add or update entries for:
- Decisions made this session (what, why, what alternatives were considered)
- Technical gotchas discovered
- Any durable information that would help future sessions
Do NOT duplicate information already in CLAUDE.md. MEMORY.md is for accumulated knowledge, not permanent reference.
Step 4: Update ORIENT.md (if needed)
Only if:
- New scripts or common operations were added
- Project shape changed (new directories, reorganization)
- Known weirdness changed
Step 5: Update CLAUDE.md (if needed)
Only if:
- New conventions were established
- Schema changed
- Architecture changed in ways that affect agent behavior
Step 6: Present Summary
Show the user a brief summary of what was updated:
- Files modified
- Key items recorded
- Next steps noted
Rules
- Read each COMP file before editing it
- Don't duplicate information across COMP files
- Keep entries concise — future sessions need scannable notes, not essays
- If nothing meaningful happened this session, say so rather than adding noise
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

