SEPCC
AGENTS.md38 starsChanged 6 months agoMITView on GitHub
This file is identical to CLAUDE.md. Keep them in sync.
- Pipes a download into a shell
- Reads credentials
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 repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- context-recallSkill
- handoff-writerSkill
- route-taskSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
19 rules. About 0 are common, 6 are distinctive, and 13 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
13
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Always use uv run to run files instead of the global python command.
- Very specific: line 11
Read .env.example for environment variables.
- Distinctive: line 12
All CI checks must pass; failing checks block merge.
- Very specific: line 13
Add tests for new changes (including edge cases), then run uv run pytest.
- Very specific: line 14
Run checks in this order: uv run ruff format, uv run ruff check, uv run ty check, uv run pytest.
- Very specific: line 15
Do not add # type: ignore or # ty: ignore.
- Very specific: line 16
All 5 checks are enforced in tests.yml on push/merge (parallel jobs: suppression grep, ruff-format, ruff-check, ty, pytest).
- Very specific: line 27
Shared utilities: Put shared Anthropic protocol logic in neutral core/anthropic/ modules.
- Very specific: line 29
Encapsulation: Use accessor methods for internal state (e.g.
- Very specific: line 30
Provider-specific config: Keep provider-specific fields (e.g.
- Very specific: line 31
Dead code: Remove unused code, legacy systems, and hardcoded values.
- Very specific: line 32
Performance: Use list accumulation for strings (not += in loops), cache env vars at init, prefer iterative over recursive when stack depth …
- Very specific: line 33
Platform-agnostic naming: Use generic names (e.g. PLATFORM_EDIT) not platform-specific ones (e.g.
- Very specific: line 34
No type ignores: Do not add # type: ignore or # ty: ignore.
- Distinctive: line 35
Complete migrations: When moving modules, update imports to the new owner and remove old compatibility shims in the same change unless …
- Distinctive: line 40
ANALYZE: Read relevant files. Do not guess.
- Distinctive: line 43
VERIFY: Run ci checks and relevant smoke tests.
- Distinctive: line 44
SPECIFICITY: Do exactly as much as asked.
- Distinctive: line 54
Prefer built-in tools (grep, read_file, etc.) over manual workflows.
≈ “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
AGENTIC DIRECTIVE
This file is identical to CLAUDE.md. Keep them in sync.
CODING ENVIRONMENT
- Install astral uv using "curl -LsSf https://astral.sh/uv/install.sh | sh" if not already installed and if already installed then update it to the latest version
- Install Python 3.14.0 stable using
uv python install 3.14.0if not already installed (requires uv >=0.9; see[tool.uv] required-versioninpyproject.toml) - Always use
uv runto run files instead of the globalpythoncommand. - Current uv ruff formatter is set to py314 which has supports multiple exception types without paranthesis (except TypeError, ValueError:)
- Read
.env.examplefor environment variables. - All CI checks must pass; failing checks block merge.
- Add tests for new changes (including edge cases), then run
uv run pytest. - Run checks in this order:
uv run ruff format,uv run ruff check,uv run ty check,uv run pytest. - Do not add
# type: ignoreor# ty: ignore; fix the underlying type issue. - All 5 checks are enforced in
tests.ymlon push/merge (parallel jobs: suppression grep, ruff-format, ruff-check, ty, pytest). - Branch protection: set required status checks to all of those statuses (e.g. Ban type ignore suppressions, ruff-format, ruff-check, ty, pytest—use the exact labels GitHub shows, which may be prefixed with CI /). Remove ci from required checks if it was previously added for the old gate job.
IDENTITY & CONTEXT
- You are an expert Software Architect and Systems Engineer.
- Goal: Zero-defect, root-cause-oriented engineering for bugs; test-driven engineering for new features. Think carefully; no need to rush.
- Code: Write the simplest code possible. Keep the codebase minimal and modular.
ARCHITECTURE PRINCIPLES
- Shared utilities: Put shared Anthropic protocol logic in neutral
core/anthropic/modules. Do not have one provider import from another provider's utils. - DRY: Extract shared base classes to eliminate duplication. Prefer composition over copy-paste.
- Encapsulation: Use accessor methods for internal state (e.g.
set_current_task()), not direct_attributeassignment from outside. - Provider-specific config: Keep provider-specific fields (e.g.
nim_settings) in provider constructors, not in the baseProviderConfig. - Dead code: Remove unused code, legacy systems, and hardcoded values. Use settings/config instead of literals (e.g.
settings.provider_typenot"nvidia_nim"). - Performance: Use list accumulation for strings (not
+=in loops), cache env vars at init, prefer iterative over recursive when stack depth matters. - Platform-agnostic naming: Use generic names (e.g.
PLATFORM_EDIT) not platform-specific ones (e.g.TELEGRAM_EDIT) in shared code. - No type ignores: Do not add
# type: ignoreor# ty: ignore. Fix the underlying type issue. - Complete migrations: When moving modules, update imports to the new owner and remove old compatibility shims in the same change unless preserving a published interface is explicitly required.
- Maximum Test Coverage: There should be maximum test coverage for everything, preferably live smoke test coverage to catch bugs early
COGNITIVE WORKFLOW
- ANALYZE: Read relevant files. Do not guess.
- PLAN: Map out the logic. Identify root cause or required changes. Order changes by dependency.
- EXECUTE: Fix the cause, not the symptom. Execute incrementally with clear commits.
- VERIFY: Run ci checks and relevant smoke tests. Confirm the fix via logs or output.
- SPECIFICITY: Do exactly as much as asked; nothing more, nothing less.
- PROPAGATION: Changes impact multiple files; propagate updates correctly.
SUMMARY STANDARDS
- Summaries must be technical and granular.
- Include: [Files Changed], [Logic Altered], [Verification Method], [Residual Risks] (if no residual risks then say none).
TOOLS
- Prefer built-in tools (grep, read_file, etc.) over manual workflows. Check tool availability before use.
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.

