agents_driven_sdlc
AGENTS.md1 starsChanged 19 days agoMITView on GitHub
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 repository9 other files it gives its agents.
- define-product-changeSkill
- design-project-architectureSkill
- design-test-scenariosSkill
- develop-user-scenariosSkill
- mediate-solutionSkill
- orchestratorSkill
- plan-change-implementationSkill
- review-solutionSkill
- ux-designerSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 4
Do not add component names, documentation paths, infrastructure constraints, or other project-specific rules to shared skills.
- Very specific: line 9
Keep agents/openai.yaml consistent with SKILL.md.
- Very specific: line 11
After changes, validate frontmatter and structure using the standard quick_validate.py from skill-creator.
- Very specific: line 12
Check installer syntax with node --check scripts/install.cjs and run npm test.
- Very specific: line 13
Do not copy skills or agents into projects.
- Very specific: line 14
Keep mistakes.md local; do not add it to Git.
≈ “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
Purpose
- This repository contains shared Codex skills and agents for agent-driven software development.
- Do not add component names, documentation paths, infrastructure constraints, or other project-specific rules to shared skills. Such rules belong in the relevant project's
AGENTS.md.
Structure and Validation
- Each skill lives in
skills/<skill-name>and containsSKILL.md. - Keep
agents/openai.yamlconsistent withSKILL.md. - Each custom agent lives in
agents/<agent-name>.toml. Do not duplicate instructions from the skill it is based on. - After changes, validate frontmatter and structure using the standard
quick_validate.pyfromskill-creator. - Check installer syntax with
node --check scripts/install.cjsand runnpm test. - Do not copy skills or agents into projects. For local use, run
node scripts/install.cjs, which copies the bundle to the user directory~/.agents/skills/agents_driven_sdlc/. Install or reinstall only when the user explicitly requests it. - Keep
mistakes.mdlocal; do not add it to Git.
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.

