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/pvliesdonk/openapi-mcp/claude-mdgit clone --depth 1 https://github.com/pvliesdonk/openapi-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/pvliesdonk/openapi-mcp/claude-md)<a href="https://agentmods.dev/instructions/pvliesdonk/openapi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pvliesdonk/openapi-mcp/claude-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 5.1 | $0.05555 | $0.05555 |
| Opus 5 | $0.02778 | $0.02778 |
| Sonnet 5 | $0.01111 | $0.01111 |
| Haiku 4.5 | $0.00556 | $0.00556 |
Grade A, and why
openapi-mcp CLAUDE.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 5d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAPI MCP
A generic MCP server that builds its tools at runtime from any OpenAPI specification.
Design
This sibling derives its domain tools from an OpenAPI spec at boot rather than
hand-writing them. The only departure from a stock generated project is
make_server() (loads+validates the spec, builds the upstream client, wires
OpenAPIProvider) and the plain-Python spec/auth core in domain.py
(load_spec, resolve_base_url, required_schemes, build_upstream_client).
Inbound auth (who may call this server) is inherited from pvl-core; upstream
auth (OAPI_SECURITY_*, how this server talks to the wrapped API) is the only
new auth surface. Keep the two strictly separate.
Project Structure
Conventions
- Python 3.11+
uvfor package management,rufffor linting/formatting (line length 88)hatchlingbuild backend- Conventional commits:
feat:,fix:,docs:,refactor:,test:,chore: - Google-style docstrings on all public functions
logging.getLogger(__name__)throughout, noprint()- Type hints everywhere
- Tests:
pytestwith fixtures intests/fixtures/
Hard PR Acceptance Gates
Every PR must pass all of the following before merge. Do not open or push a PR until these are green locally:
- CI passes —
uv run pytest -x -qall tests pass - Lint passes — run in this exact order:
uv run ruff check --fix .thenuv run ruff format .then verify withuv run ruff format --check .. Always run format after check --fix because check --fix can leave files needing reformatting. - Type-check passes —
uv run mypy src/ tests/reports no errors - Patch coverage ≥ 80% — Codecov measures only lines added/changed in the PR diff. Run
uv run pytest --cov=<changed_module> --cov-report=term-missingand verify new code is exercised. Add tests for every uncovered branch before pushing.
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.
- 5d ago First seen · 274 lines · 5,555 tokens per session scan A 82f5c067550a
openapi-mcp CLAUDE.md is an instructions file published in the GitHub repository pvliesdonk/openapi-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 5,555 tokens to every session, about $0.0278 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.