skills
AGENTS.md1 starsChanged 58 days agoBSD-2-ClauseView on GitHub
Before contribution work, read .github/copilot-instructions.md and follow it as the canonical source for project philosophy, pull request requirements, validation gates, strict negative constraints, and before-commit workflow.
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 31,439 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 repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- code-tidySkill
- curate-releaseSkill
- customer-strategy-forgeSkill
- designing-for-intentSkill
- feature-to-planSkill
- go-testable-designSkill
- instruction-styleSkill
- issue-refine-loopSkill
- mutation-hunterSkill
- optimize-prompt-loopSkill
- plan-to-graphSkill
- rugged-evil-testerSkill
- skill-reviewerSkill
- spec-auditorSkill
- to-earsSkill
- triaging-pr-reviewsSkill
The file
We split this AGENTS.md into the rules it gives an agent
12 rules. About 0 are common, 0 are distinctive, and 12 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.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Before contribution work, read .github/copilot-instructions.md and follow it as the canonical source for project philosophy, pull request …
- Very specific: line 9
When updating project conventions, pull request requirements, validation gates, or core mandates, make those changes in …
- Very specific: line 12
Use the available Agent Skills when their descriptions match the task.
- Very specific: line 13
Use the configured MCP servers in .mcp.json when you need current documentation, lousy-agents analysis, or structured reasoning.
- Very specific: line 14
Keep shared policy DRY: do not duplicate validation, PR, or commit rules here.
- Very specific: line 17
Use the commands documented in the canonical .github/copilot-instructions.md Commands section.
- Very specific: line 20
Follow the canonical .github/copilot-instructions.md Validation section.
- Very specific: line 23
Follow the canonical .github/copilot-instructions.md Verification section.
- Very specific: line 26
Follow the canonical .github/copilot-instructions.md Feedback Loop section.
- Very specific: line 29
Follow the canonical .github/copilot-instructions.md Mandatory section.
- Very specific: line 32
Follow the canonical .github/copilot-instructions.md Before Commit section.
- Very specific: line 35
Follow the canonical .github/copilot-instructions.md Validation Suite section.
≈ “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.
Files
Lousy Agents Skills - Codex and Copilot CLI Context
Source of Truth
The shared contribution policy for this repository lives in .github/copilot-instructions.md.
Before contribution work, read .github/copilot-instructions.md and follow it as the canonical source for project philosophy, pull request requirements, validation gates, strict negative constraints, and before-commit workflow.
Agentic Parity Mandate
When updating project conventions, pull request requirements, validation gates, or core mandates, make those changes in .github/copilot-instructions.md, not this file. This file should only contain Codex and Copilot CLI operational routing.
Codex and Copilot CLI Workflow Instructions
- Use the available Agent Skills when their descriptions match the task.
- Use the configured MCP servers in
.mcp.jsonwhen you need current documentation, lousy-agents analysis, or structured reasoning. - Keep shared policy DRY: do not duplicate validation, PR, or commit rules here. Follow the "Before Commit" and "Mandatory" sections of
.github/copilot-instructions.mdfor the canonical requirements.
Commands
Use the commands documented in the canonical .github/copilot-instructions.md Commands section.
Validation
Follow the canonical .github/copilot-instructions.md Validation section.
Verification
Follow the canonical .github/copilot-instructions.md Verification section.
Feedback Loop
Follow the canonical .github/copilot-instructions.md Feedback Loop section.
Mandatory
Follow the canonical .github/copilot-instructions.md Mandatory section.
Before Commit
Follow the canonical .github/copilot-instructions.md Before Commit section.
Validation Suite
Follow the canonical .github/copilot-instructions.md Validation Suite section.
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.