MythOs_Aegis
AGENTS.md0 starsChanged 3 months agoApache-2.0View on GitHub
When a user asks to optimize, benchmark, evaluate, or improve a Markdown-based agent skill, use the repo-local skill-optimizer skill in .agents/skills/skill-optimizer/. Do not rewrite a skill from intuition alone. For optimization work: 1. Preserve the original SKILL.md. 2. Establish a baseline before edits. 3. Use separate train, validation, and test splits. 4. Keep edits bounded and traceable. 5. Accept changes only after held-out validation. 6. Record rejected edits and regressions. 7. Keep the test split isolated until final evaluation. Store…
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 31,774 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 repository46 other files it gives its agents.
- academixSkill
- agent-browserSkill
- ai-engineering-platformSkill
- apocalypseSkill
- aria-apg-reviewSkill
- context-budgetSkill
- crawler-readiness-auditSkill
- data-protection-gateSkill
- decision-criticality-gateSkill
- fact-checkerSkill
- find-skillsSkill
- focus-friendly-outputSkill
- frontend-designSkill
- grill-meSkill
- grill-with-docsSkill
- humanizerSkill
- improve-codebase-architectureSkill
- microsoft-foundrySkill
- output-templatesSkill
- pre-launch-security-gateSkill
- prompt-preflightSkill
- quick-recapSkill
- rag-retrieval-qualitySkill
- rest-api-best-practicesSkill
- rigorous-responseSkill
- security-checklistSkill
- shepherdSkill
- skill-optimizerSkill
- sql-query-correctnessSkill
- system-design-scaleSkill
- tddSkill
- ui-ux-color-contrastSkill
- ui-ux-component-qualitySkill
- ui-ux-design-systemsSkill
- ui-ux-dropdownsSkill
- ui-ux-form-validationSkill
- ui-ux-generationSkill
- ui-ux-loading-statesSkill
- ui-ux-mobile-cssSkill
- ui-ux-typographySkill
- ux-logic-loopSkill
- ux-pattern-reviewSkill
- vercel-react-best-practicesSkill
- visual-flow-storyboardSkill
- visual-pr-reviewSkill
- web-design-guidelinesSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 5
When a user asks to optimize, benchmark, evaluate, or improve a Markdown-based agent skill, use the repo-local skill-optimizer skill in …
- Distinctive: line 6
Do not rewrite a skill from intuition alone.
- Distinctive: line 11
Use separate train, validation, and test splits.
- Distinctive: line 12
Keep edits bounded and traceable.
- Distinctive: line 15
Keep the test split isolated until final evaluation.
- Very specific: line 21
When a response needs structure, use the shared templates in .agents/skills/output-templates/SKILL.md instead of inventing a new format per …
- Very specific: line 22
Keep the main response aligned to one of those templates, then end every substantive response with the Quick Recap footer from …
≈ “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
Agent Instructions
Skill Optimization
When a user asks to optimize, benchmark, evaluate, or improve a Markdown-based agent skill, use the repo-local skill-optimizer skill in .agents/skills/skill-optimizer/.
Do not rewrite a skill from intuition alone.
For optimization work:
- Preserve the original
SKILL.md. - Establish a baseline before edits.
- Use separate train, validation, and test splits.
- Keep edits bounded and traceable.
- Accept changes only after held-out validation.
- Record rejected edits and regressions.
- Keep the test split isolated until final evaluation.
Store optimization artifacts under runs/.
Shared Output Templates
When a response needs structure, use the shared templates in .agents/skills/output-templates/SKILL.md instead of inventing a new format per skill.
Keep the main response aligned to one of those templates, then end every substantive response with the Quick Recap footer from .agents/skills/quick-recap/SKILL.md.
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.