DROOdotFOODROOdotFOO/agent-skills/AGENTS.md

agent-skills

AGENTS.md1 starsChanged 2 months agoMITView on GitHub

This repository contains portable SKILL.md workflows and nine standalone Python agent CLIs that also expose MCP servers. Raxol, Codex, and Claude Code must consume the same skill instructions without host-specific assumptions. - Every skill directory has a SKILL.md whose name matches the directory. - Descriptions contain specific TRIGGER when: and DO NOT TRIGGER boundaries. - Keep workflows capability-based. When hosts differ, document explicit Codex, Claude Code, and Raxol branches instead of assuming one tool name or config path. - Supporting…

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

9 rules. About 0 are common, 4 are distinctive, and 5 are 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Run ./scripts/skills-lint.sh after changing any skill.
line 11
Very specific:
Run python3 scripts/skill-triggers-test.py after changing skill discovery text.
line 12
Very specific:
Run python3 scripts/codex-compat-test.py after changing skills or plugin metadata.
line 13
Distinctive:
Run the affected agent's pytest suite after changing Python code.
line 14
Very specific:
Keep shell scripts set -euo pipefail and shellcheck-clean.
line 15
Distinctive:
Keep Python typed and formatted with Ruff.
line 16
Very specific:
Every skill directory has a SKILL.md whose name matches the directory.
line 20
Distinctive:
Keep workflows capability-based.
line 22
Distinctive:
Do not add empty modules, placeholder skills, or claims about unavailable tools.
line 26

≈ “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

Repository purpose

This repository contains portable SKILL.md workflows and nine standalone Python agent CLIs that also expose MCP servers. Raxol, Codex, and Claude Code must consume the same skill instructions without host-specific assumptions.

Required checks

Run ./scripts/skills-lint.sh after changing any skill.
Run python3 scripts/skill-triggers-test.py after changing skill discovery text.
Run python3 scripts/codex-compat-test.py after changing skills or plugin metadata.
Run the affected agent's pytest suite after changing Python code.
Keep shell scripts set -euo pipefail and shellcheck-clean.
Keep Python typed and formatted with Ruff.

Skill rules

Every skill directory has a SKILL.md whose name matches the directory.
Descriptions contain specific TRIGGER when: and DO NOT TRIGGER boundaries.
Keep workflows capability-based. When hosts differ, document explicit Codex, Claude Code, and Raxol branches instead of assuming one tool name or config path.
Supporting Markdown files retain their impact, impactDescription, and comma-separated tags frontmatter.
Do not add empty modules, placeholder skills, or claims about unavailable tools.

Distribution boundaries

.codex-plugin/plugin.json is the Codex plugin entry point.
.claude-plugin/ remains the Claude Code marketplace entry point.
The public plugin is skills-only. Agent CLIs and MCP servers require separate installation and host configuration.
skills/cancer-predisposition-variant-analyst is an optional git submodule; do not count it as part of archive or plugin installs unless it is populated.

Download now (ZIP)

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 28,693 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 repository61 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adversarial-reviewerSkill
- agent-designerSkill
- architectSkill
- autoresearchSkill
- blockscoutSkill
- ci-cd-pipeline-builderSkill
- claude-apiSkill
- codebase-onboardingSkill
- code-reviewSkill
- coingeckoSkill
- database-designerSkill
- dependency-auditorSkill
- design-uxSkill
- digestSkill
- droo-stackSkill
- env-secrets-managerSkill
- ethskillsSkill
- ffmpeg-asmSkill
- focused-fixSkill
- frontend-slop-auditSkill
- git-guardrailsSkill
- git-worktree-managerSkill
- humanizerSkill
- interface-designerSkill
- llm-cost-optimizerSkill
- local-browser-inspectorSkill
- mcp-server-builderSkill
- native-codeSkill
- nixSkill
- noirSkill
- observability-designerSkill
- patchbotSkill
- performance-profilerSkill
- playwrightSkill
- polymathSkill
- prd-to-planSkill
- prepperSkill
- property-testingSkill
- qaSkill
- rag-architectSkill
- raxol-paymentsSkill
- raxolSkill
- raxol-symphonySkill
- recallSkill
- refactoring-strategySkill
- regenSkill
- releaseSkill
- security-auditorSkill
- self-improving-agentSkill
- sentinelSkill
- signozSkill
- skill-creatorSkill
- solidity-auditorSkill
- tddSkill
- tech-debt-trackerSkill
- ubiquitous-languageSkill
- watchdogSkill
- web-asset-generatorSkill
- writing-voiceSkill
- The first 60 shown.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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