skills
AGENTS.md8 starsChanged 5 months agoMITView on GitHub
@/Users/matt/.codex/RTK.md This repository ships skills for Codex and Claude Code. Use .claude-plugin/plugin.json and .codex-plugin/plugin.json for the canonical skill inventory; keep their skill lists and release versions synchronized. skills/core/ contains original workflows and skills/gstack/ contains adapted workflows. Supporting commands, hooks and scripts live in their named root directories. Keep skills focused on non-obvious decisions and real workflow invariants. Inherit the user's active model unless an explicit orchestration role configuration applies. Load conditional references only when relevant. Runtime-specific metadata, tools and session…
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 32,671 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 repository32 other files it gives its agents.
- agents-md-lintSkill
- auto-scopeSkill
- cavemanSkill
- completeSkill
- councilSkill
- deskSkill
- discernmentSkill
- doSkill
- dreamSkill
- handoffSkill
- humanizeSkill
- laymanSkill
- offloadSkill
- prototypeSkill
- pr-reviewSkill
- red-penSkill
- review-securitySkill
- session-budgetSkill
- writing-commitsSkill
- writing-plan-documentsSkill
- writing-sqlSkill
- design-consultationSkill
- design-reviewSkill
- investigateSkill
- plan-deep-reviewSkill
- plan-design-reviewSkill
- plan-devex-reviewSkill
- plan-eng-reviewSkill
- plan-sessionSkill
- qa-onlySkill
- qaSkill
- reviewSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Keep skills focused on non-obvious decisions and real workflow invariants.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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.
Files
@/Users/matt/.codex/RTK.md
Bork skill library
This repository ships skills for Codex and Claude Code. Use .claude-plugin/plugin.json and .codex-plugin/plugin.json for the canonical skill inventory; keep their skill lists and release versions synchronized. skills/core/ contains original workflows and skills/gstack/ contains adapted workflows. Supporting commands, hooks and scripts live in their named root directories.
Keep skills focused on non-obvious decisions and real workflow invariants. Inherit the user's active model unless an explicit orchestration role configuration applies. Load conditional references only when relevant. Runtime-specific metadata, tools and session IDs are not interchangeable.
Preserve intentional formatting rules, frozen acceptance criteria, ownership checks and independent review evidence. Report missing verification honestly. Recommendation-only work must not mutate skills; authorized changes must preserve unrelated dirt. Do not commit or push unless requested.
For validation, bash scripts/test-all.sh is the one command that runs every check (the structure validator, both Python suites, every Node test and every shell test) and prints one summary line per group; CI runs it on every push and pull request to main. While iterating, use ruby scripts/validate-skills.rb and the relevant helper tests. python3 -m unittest discover -s scripts -p 'test_*.py' covers Python helpers; Node helper tests are colocated with their implementations. Prompt eval cases live under evals/ and measure behavior separately from structural validation.
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
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.

