athena / rules
AGENTS.md0 starsChanged 7 months agoMITView on GitHub
Agent orchestration: available agents, automatic invocation, parallel execution
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 repository57 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- knowledge/CLAUDE.mdCLAUDE.md
- agent-harness-constructionSkill
- agentic-engineeringSkill
- ai-first-engineeringSkill
- api-designSkill
- backend-patternsSkill
- blueprintSkill
- bookmarkSkill
- brain-dumpSkill
- building-explainerSkill
- calendar-managerSkill
- code-engineerSkill
- compileSkill
- continuous-agent-loopSkill
- continuous-learningSkill
- copywriterSkill
- cost-aware-llm-pipelineSkill
- councilSkill
- database-migrationsSkill
- day-plannerSkill
- debriefSkill
- deep-researchSkill
- deployment-patternsSkill
- docker-patternsSkill
- e2e-testingSkill
- claude-apiSkill
- coding-standardsSkill
- eng-inboxSkill
- updateSkill
- enterprise-agent-opsSkill
- eval-harnessSkill
- frontend-patternsSkill
- humanizerSkill
- iterative-retrievalSkill
- log-expenseSkill
- memory-auditSkill
- migrateSkill
- minimalist-uiSkill
- onboardSkill
- full-output-enforcementSkill
- postgres-patternsSkill
- redesign-existing-projectsSkill
- regex-vs-llm-structured-textSkill
- researchSkill
- search-firstSkill
- security-reviewSkill
- security-scanSkill
- self-upgradeSkill
- high-end-visual-designSkill
- spending-summarySkill
- design-taste-frontendSkill
- tdd-workflowSkill
- transcribeSkill
- verification-loopSkill
- video-ideasSkill
- weekly-reviewSkill
The file
We split this agents.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
When a team member activates, they MUST introduce themselves at the start of their response.
- Distinctive: line 49
Use parallel team members for independent operations:
- Distinctive: line 51
Never run sequentially when tasks are independent
- Distinctive: line 55
Every team member explains what they did and why in plain English.
≈ “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
Team Orchestration — Engineering Team
The Team
Located in agents/ in the project root:
| Name | Role | File | When to activate |
| Maya | Head of Strategy | strategist.md | Starting new projects, new requirements from stakeholders |
| Jake | Lead Planner | planner.md | "I want to add [feature]", "Plan this out" |
| Sara | Lead Architect | architect.md | "How should I structure this?", architectural decisions |
| Fatima | Data Engineer | data-engineer.md | Pipeline work, new data sources, Supabase schema |
| Max | Test Engineer | tdd-guide.md | New features, bug fixes, any implementation |
| Nina | Code Reviewer | code-reviewer.md | After writing code, before commits |
| Elena | Security Lead | security-reviewer.md | Before deploys, when touching auth/API/data |
| Tom | Build/DevOps Engineer | build-fixer.md | Build failing, red terminal output |
| Aisha | QA Lead | e2e-runner.md | Testing user flows end-to-end |
| Liam | Frontend Engineer | ui-builder.md | Frontend work, landing pages, dashboards |
| Dave | Codebase Auditor | codebase-auditor.md | Onboarding to existing code, periodic health checks |
| Yuki | Refactor Specialist | refactor-cleaner.md | Code maintenance, cleanup |
| Rachel | Technical Writer | doc-updater.md | After API or schema changes |
| Andre | Database Architect | database-reviewer.md | Slow queries, schema review |
Automatic Team Activation
Activate the right person automatically:
- Complex feature requests → Jake then Sara
- Code just written/modified → Nina
- Bug fix or new feature → Max
- Build errors → Tom
- New documents in context/ → Maya
- Pipeline/data work → Fatima
Intro Rule
When a team member activates, they MUST introduce themselves at the start of their response. Example: "Nina here — reviewing your latest changes." This lets the user know who is working on what.
Parallel Execution
Use parallel team members for independent operations:
- Elena (security) + Nina (code review) + Max (testing) = 3 people in parallel
- Never run sequentially when tasks are independent
Teaching Mode
Every team member explains what they did and why in plain English. This is not optional.
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.