Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bnjam/stac-mcp/agents-mdgit clone --depth 1 https://github.com/BnJam/stac-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/bnjam/stac-mcp/agents-md)<a href="https://agentmods.dev/instructions/bnjam/stac-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bnjam/stac-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02629 | $0.02629 |
| Opus 5 | $0.01314 | $0.01314 |
| Sonnet 5 | $0.00526 | $0.00526 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
stac-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents / Contributor Guide — Python best practices & PEP adherence
Purpose
- Provide concise, actionable guidance for contributors and automated agents working on this repository.
- Emphasize adherence to Python PEPs (style, typing, docstrings) and the project's tooling.
Core principles
- Follow PEP 8 for style and naming (use snake_case for functions/variables, PascalCase for classes, UPPER_SNAKE for constants).
- Use PEP 257 docstrings for modules, classes, and public functions/methods.
- Prefer type hints (PEP 484). Keep signatures explicit and avoid overly broad Any where a concrete type helps readability.
- Always import generics from the
typingmodule (List, Dict, Optional, Union, Tuple, Set, Iterable, Callable, etc.) instead of using builtin collection annotations likelist[str]unless an ADR supersedes this rule. This maintains consistency across the codebase and clarifies intent for contributors and automated agents. - Keep functions small and single-responsibility. Favor composition over inheritance when appropriate.
Public-API-first rule
- Prefer using public, documented APIs of third-party libraries. Do not reach into private or underscore-prefixed attributes or functions (for example, avoid accessing objects like
client._stac_io,session._pool, or other internals). - When interacting with STAC libraries prefer the public Client/IO abstractions (for example,
pystac_client.Clientandpystac.stac_io.StacIO/StacApiIO) or perform explicit HTTP calls withrequestsrather than reading or mutating private internals.
These rules keep behavior stable across upstream library upgrades and make code easier to test and maintain.
Formatting & Linting: Pre-Commit/Pre-Push Checklist
MUST run these commands and ensure they pass before every git commit and git push.
- Format Code:
uv run ruff format stac_mcp/ tests/ examples/ - Lint and Auto-Fix:
uv run ruff check stac_mcp/ tests/ examples/ --fix --no-cache - Run Tests:
uv run pytest -q - Verify Test Coverage:
uv run coverage run -m pytest -v uv run coverage report --fail-under=85
IMPORTANT: Run the ruff format and ruff check commands multiple times in sequence to ensure all issues are resolved, as auto-fixing can sometimes introduce new formatting needs.
Testing & validation
- Write tests for behavior, not implementation; prefer parametrized tests for similar cases.
- Run the full test suite locally:
- pytest -v
- Ensure all tests pass before pushing.
- Follow the repository's Validation checklist:
- Ruff format and lint pass.
- All tests pass.
Logging & errors
- Use the standard logging module; configure logging at entrypoints only.
- Do not swallow exceptions silently. Surface useful context and wrap exceptions only when adding helpful information.
- Avoid print() for diagnostics in library code.
Async & IO
- Prefer async APIs when interacting with network or IO in the MCP server; follow standard asyncio patterns.
- Avoid blocking calls in async code. Use run_in_executor for CPU-bound or blocking work.
Dependencies & environment
- Use virtual environments or tox for isolation.
- Pin dev dependencies in pyproject.toml where appropriate.
- Install in editable mode during development: pip install -e ".[dev]"
Commit & PR guidance
- Write clear commit messages with intent and scope.
- Run formatting and tests before pushing.
- Keep PRs focused and small; include a brief description of changes and validation steps.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 212 lines · 2,629 tokens per session scan A d04dd39422c7
stac-mcp AGENTS.md is an instructions file published in the GitHub repository BnJam/stac-mcp (13 stars, last pushed 27d ago), licensed MIT. It adds 2,629 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
VCVio AGENTS.md
Instructions for Verified-zkEVM/VCVio, covering vcvio — ai agent guide, fast start, attribution, headers, and docstrings, module scopes and what this project is.
co-mathematician CLAUDE.md
Instructions for VeryMath/co-mathematician, covering claude.md, repository contract, required flow, claude code operating notes and harness commands.
SutroYaro GEMINI.md
Instructions for cybertronai/SutroYaro, covering gemini.md - sutro group research workspace, project context, read these first, core concepts and current best methods.
gpu-ai-skills CLAUDE.md
Instructions for intel/gpu-ai-skills, covering claude.md, what this repository is, repository structure, commands and validation (required before any skill change).
mcp-pubmed-server-pancrpal CLAUDE.md
Instructions for PancrePal-xiaoyibao/mcp-pubmed-server-pancrpal, covering claude.md, project overview, commands, architecture and mcp tools (8 total).
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.