agentleFS
Sign inStart free
NashEQifyNashEQify/forge/AGENTS.md

forge

AGENTS.md2 starsChanged 3 days agoMITView on GitHub

Read and follow framework/work-principle.md before taking up work. Resolve this reference against the framework root; retain the consumer CWD. Reread it after compaction. Forge's shared git hooks run when installed in the active repository: pre-commit.sh (pre-commit, pre-merge-commit and commit-msg; PLAN-VALIDATE / CG-CONV / SKILL-FM-VALIDATE BLOCK; SECRET-SCAN / SOURCE-VERIFICATION WARN). The two SessionStart scripts are Claude-specific and conditional, not universal Codex boot hooks. Codex uses the managed AGENTS entry installed by scripts/setup-codex.sh; its loading must be checked in a fresh session.…

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

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Very specific:

    Read and follow framework/work-principle.md before taking up work.

    line 3
  2. Distinctive:

    After compaction, reread before continuing every file in the boot entry's post-compaction reread list.

    line 11
  3. Distinctive:

    Default language for all new work is English.

    line 22
  4. Distinctive:

    Write code comments, specs, ADRs, task content, and review artifacts in English.

    line 23
  5. Distinctive:

    Use German only when quoting existing German source text verbatim or when the user explicitly requests German output.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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

Buddy — Codex / OpenCode Adapter

Read and follow framework/work-principle.md before taking up work. Resolve this reference against the framework root; retain the consumer CWD. Reread it after compaction.

Boot

Load and follow: the resolved soul (framework/user-scope.md; default agents/buddy/soul.md), framework/invariants.md, agents/buddy/operational.md, agents/buddy/boot.md. After compaction, reread before continuing every file in the boot entry's post-compaction reread list.

Framework-wide rules

Workflow selection, intent-driven work, the invariants (numbered as cited elsewhere: "Inv 4" and so on) and observability hold in every project and live in framework/invariants.md; read and follow it before taking up work (the boot entry names it). This file adds the host's load list and the rules that apply only when the active project is the forge repository itself.

Language Policy

  • Default language for all new work is English.
  • Write code comments, specs, ADRs, task content, and review artifacts in English.
  • Use German only when quoting existing German source text verbatim or when the user explicitly requests German output.

Frozen Zones + Consistency

SoT: docs/STRUCTURE.md. Consistency cascade: context-rules.md.

Commit

Format and types are enforced by the pre-commit hook (CG-CONV).

Active Hooks

Forge's shared git hooks run when installed in the active repository: pre-commit.sh (pre-commit, pre-merge-commit and commit-msg; PLAN-VALIDATE / CG-CONV / SKILL-FM-VALIDATE BLOCK; SECRET-SCAN / SOURCE-VERIFICATION WARN). The two SessionStart scripts are Claude-specific and conditional, not universal Codex boot hooks. Codex uses the managed AGENTS entry installed by scripts/setup-codex.sh; its loading must be checked in a fresh session. The framework runs no tool-event hooks (PreToolUse / PostToolUse / UserPromptSubmit); write-time discipline is protocol-anchored via protocols + operational.md.

OC Constraints

The consumer repo is the CWD; the framework is mounted via the OpenCode launcher ($FRAMEWORK_DIR/orchestrators/opencode/bin/oc, with OPENCODE_CONFIG_DIR=$FRAMEWORK_DIR/orchestrators/opencode/.opencode). A consumer's project-level AGENTS.md (in the consumer repo root) adds to this framework AGENTS.md, it doesn't replace it. Commands are trigger words without a prefix (wakeup, save, checkpoint, think!). OpenCode follows the same protocol-based method. Its launcher, instruction loading, permissions and actually installed Git checks must be verified for that host. Shared methodology does not establish identical execution or enforcement. There is no tool-event (PreToolUse/PostToolUse) hook layer on either harness.

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