Loop triage
Skill rossinsilico/loop-anything/templates/loop-pack/skills/loop-triage
Make Codex and Claude loop orchestration easier and more powerful.
npx -y skills add rossinsilico/loop-anything --skill loop-triageAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Select one bounded task for an agent loop from visible state, real repo evidence, permission boundaries, and a named proof command.
SKILL.md
1.0 KB, 186 tokens by cl100k_base, as published. Nobody here has run it
Loop Triage
Use this skill at the start of a loop iteration.
Inputs
loop-state.mdloop-contract.md- Current repository state
- Any explicit human instruction for this run
Process
- Read
loop-state.mdandloop-contract.md. - Inspect the real target named by the state board.
- Identify candidate tasks that fit inside one loop iteration.
- Select exactly one task.
- Name the proof command before implementation starts.
- Stop if the task needs destructive action, hidden credentials, or a broader permission boundary than the state board allows.
Output
Write or update the Active Task section in loop-state.md with:
- task
- reason
- expected files or services
- proof command
- stop condition
Do not implement until the active task and proof command are clear.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most debug triage skills give in 186 tokens
Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07
- Investigate root cause before proposing any fixin 102 of 839, across 67 files
- Read error messages completelyin 89 of 839, across 49 files
- Create a failing test case before fixingin 84 of 839, across 46 files
- Reproduce the issue consistentlyin 82 of 839, across 41 files
- Change one variable at a timein 82 of 839, across 42 files
- Check recent changesin 74 of 839, across 36 files
- Write the regression test before fixingin 74 of 839, across 40 files
- Fix the root cause not the symptomin 60 of 839, across 45 files
- Implement a single fix at a timein 59 of 839, across 20 files
- Trace data flow backward to the sourcein 50 of 839, across 20 files
- Remove all debug instrumentationin 49 of 839, across 13 files
- Form a single hypothesisin 48 of 839, across 18 files
Said here and by no other author read
- inspect the real target repository state
- identify tasks fitting one loop iteration
- select exactly one task
- name the proof command before implementation
- write the active task to the state board
- stop if the task needs destructive action
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.