agentleFS
Sign inStart free
moah0911moah0911/aftermath/AGENTS.md

aftermath

AGENTS.md14 starsChanged 6 days agoMITView on GitHub

This repo ships Aftermath. The canonical always-on ruleset is AFTERMATH.md — the six-rung recovery ladder. OpenCode also injects it every turn via .opencode/plugins/aftermath.mjs at the active intensity (lite / full / ultra / off, default full).

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository9 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After any failure, stop at the first rung of AFTERMATH.md that holds.

    line 5
  2. Very specific:

    Keep AFTERMATH.md tiny (~dozen lines).

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md — Aftermath (post-failure recovery)

This repo ships Aftermath. The canonical always-on ruleset is AFTERMATH.md — the six-rung recovery ladder. OpenCode also injects it every turn via .opencode/plugins/aftermath.mjs at the active intensity (lite / full / ultra / off, default full).

  • After any failure, stop at the first rung of AFTERMATH.md that holds. Revert cheap damage instead of patching forward.
  • Honesty under pressure: never hide a break, never silently revert, never invent an unverified root cause.
  • Enforcement: at full/ultra OpenCode blocks destructive Bash and freezes edit/write while a failure is unresolved; Claude Code / Codex apply the same path-aware block and Edit/Write freeze in PreToolUse and deliver signals through PostToolUse/UserPromptSubmit. destructiveAllowlist handles intentional exceptions.
  • Checkpoints (OpenCode, opt-in): autoRevert: true snapshots edits at ultra and restores last-known-good on a green→red test. Manual edits are reported as conflicts, never overwritten.
  • On-demand skills live in skills/ (loaded only when their failure category fires): aftermath, test-regression, retry-loop, destructive-action, build-failure, flaky-test, dependency-failure, merge-conflict.
  • Slash commands: /aftermath [lite|full|ultra|off], /aftermath-status, /aftermath-revert, /aftermath-audit, /aftermath-log, /aftermath-checkpoint, /aftermath-init.
  • aftermath init detects stacks/test commands and writes .aftermath/config.json with safePaths (disposable artifacts) and protectedPaths (source, VCS, secrets, manifests), so destructive coverage is project-aware from the start.
  • Keep AFTERMATH.md tiny (~dozen lines). Keep host adapters thin — all behavior lives in skills/ + hooks/.

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