weave-debt
Skill5 starsChanged 2 months agoMITView on GitHub
Collect deliberate shortcuts into one ledger: `weave:` markers in the code plus the Open / blocked items and verification gaps in .weave/state.md, so a deferral cannot quietly become permanent. Use when the user says "weave debt", "/weave-debt", "what did we defer", "list the shortcuts", or "known ceilings". One-shot report, edits nothing.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/weave.mdcCursor rule
- weave-auditSkill
- weave-gainSkill
- weave-helpSkill
- weave-planSkill
- weave-promptSkill
- weave-reviewSkill
- weaveSkill
The file
Files
Weave Debt
Scan
Markers in tracked source and docs, skipping
node_modules,.git, and build output:rg -n "(#|//|--|/\*) ?weave:" .The marker convention is
weave: <ceiling>, <upgrade trigger>.- The
Open / blockedsection and unverified items in.weave/state.md, if the file exists.
Output
Grouped by file:
<file>:<line>, <what was simplified>. ceiling: <limit>. upgrade: <trigger>.
Then, from the state file:
state: <open item>. blocked by: <reason or "nothing">.
Tag any marker that names no upgrade trigger as no-trigger; those are the
ones that rot. Add git blame -L<line>,<line> owners only when asked.
End with <N> markers, <M> with no trigger, <K> open state items.
Nothing found: No weave debt. Clean ledger.
Boundaries
Reads and reports only. Writes the ledger to a file (for example
WEAVE-DEBT.md) only when asked. One-shot.
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.