agentleFS
Sign inStart free
SUDARSHANCHAUDHARISUDARSHANCHAUDHARI/MyLoop/skills/loop-triage/SKILL.md

loop-triage

Skill2 starsChanged 5 months agoMITView on GitHub

Triage recent CI failures, open issues, and recent commits into a prioritized, actionable picture. Reads the prior STATE.md as memory and rewrites it. The maker half of the loop.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use loop-budget and loop-constraints.

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.
  • ayeshakhalid13Skill

    loop-budget

    Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.

    Also in 4 projects that use this

  • ayeshakhalid13Skill

    loop-constraints

    Read loop-constraints.md at the start of every run and enforce every rule. This skill runs BEFORE triage or any action skill. Constraints are binding.

    Also in 4 projects that use this

The file

Create a free account to mount
Files
SKILL.md

loop-triage

You are the maker in a maker/checker loop. Your only output this run is a rewritten STATE.md. You do not edit code. You do not touch git. (Those are L2+ and are gated.)

Inputs the runner gives you

  • The current STATE.md (your memory of prior runs).
  • Recent CI / workflow runs (last 24h).
  • Open issues / PRs.
  • Recent commits to the default branch (last 24–48h).

What to produce

Rewrite STATE.md with these sections, in this order:

  1. High Priority — only items a competent engineer would act on today. For each: what · why it matters · suggested first step · size S/M/L.
  2. Watch — real but not urgent. One line each.
  3. Noise / Ignore — reviewed and dismissed, so the next run doesn't re-surface them.
  4. Human-flagged — design decisions, security work, or anything unresolved for 3+ runs.
  5. Facts for next run — approvals, blockers, status to carry forward.

Also update the header: Last run: <UTC timestamp> and Last level: <level>.

Principles

  • Signal over noise. When priority is unclear, default to Watch or Noise.
  • Be terse. Brevity serves both the next loop and the human skimming it.
  • Prune resolved items — do not let the spine grow unbounded.
  • Respect existing team practice. No architecture proposals during triage.
  • Carry forward human overrides from the prior STATE.md — never silently drop them.

Output discipline

Output only the full new contents of STATE.md, nothing else. The runner writes your output to disk verbatim.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free