update-tears
Skill18 starsChanged 5 months agoMITView on GitHub
Update PROJECT_CONTINUITY.md and notes.toml with current session state. Use proactively before context compaction or when switching tasks.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archeoSkill
- auditSkill
- before-editSkill
- boundary-probeSkill
- check-my-workSkill
- cqs-batchSkill
- cqs-bootstrapSkill
- cqs-planSkill
- cqsSkill
- cqs-verifySkill
- docs-reviewSkill
- groom-notesSkill
- idleSkill
- investigateSkill
- landSkill
- migrateSkill
- prSkill
- recall-gateSkill
- reindexSkill
- releaseSkill
- troubleshootSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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 26
Open Issues: Keep current — check if any listed issues were closed
- Distinctive: line 28
Architecture: Update version, test count, or structural changes if they happened
- Distinctive: line 32
Add notes for any surprises from this session via CLI:
- Distinctive: line 42
Sentiment is DISCRETE: only use -1, -0.5, 0, 0.5, 1.
- Distinctive: line 46
Don't log activity — git history has that
- Very specific: line 48
Keep PROJECT_CONTINUITY.md concise — it's read on every resume
- Distinctive: line 49
Check for dirty files with git status and note uncommitted work in Pending Changes
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Update Tears
Capture current session state to survive context compaction.
Files to update
PROJECT_CONTINUITY.md
Update these sections:
- Right Now: What you're actively working on. Include:
- Task description and date
- Branch name
- What's done in this session
- What still needs to happen
- Any open PRs
- Parked: Threads to revisit later (moved from Right Now when switching tasks)
- Open Issues: Keep current — check if any listed issues were closed
- Architecture: Update version, test count, or structural changes if they happened
docs/notes.toml
Add notes for any surprises from this session via CLI:
cqs notes add "note text" --sentiment 0.5 --mentions file.rs,concept- Bugs that were non-obvious (sentiment: -1 or -0.5)
- Patterns that worked well (sentiment: 0.5 or 1)
- Observations worth remembering (sentiment: 0)
Sentiment is DISCRETE: only use -1, -0.5, 0, 0.5, 1.
Rules
- Don't log activity — git history has that
- Focus on state that would be lost: what's in progress, what decisions were made, what's blocked
- Keep PROJECT_CONTINUITY.md concise — it's read on every resume
- Check for dirty files with
git statusand note uncommitted work in Pending Changes
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.

