swagger-docs-mcp AGENTS.md

swagger-docs-mcp AGENTS.md is an instructions file for Codex, OpenCode from qipeijun/swagger-docs-mcp. It costs 597 tokens per session, scanned A, original, MIT.

A repository instruction file for a TypeScript service that fetches and parses Swagger API documentation and exposes it through MCP tools. It describes the source folders, tests, commands, and coding conventions.

In plain words
What is it for?
Use it when developing, testing, building, or reviewing the swagger-docs-mcp repository, including its HTTP fetching, Swagger 2.0 parsing, service, server, and command-line code.
Why use it?
It gives an agent the project-specific rules needed to place code correctly, run the right checks, and avoid editing generated output.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/qipeijun/swagger-docs-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/qipeijun/swagger-docs-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for swagger-docs-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/qipeijun/swagger-docs-mcp/agents-md.svg)](https://agentmods.dev/instructions/qipeijun/swagger-docs-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/qipeijun/swagger-docs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/qipeijun/swagger-docs-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 597 This file is loaded in full into every session.
When invoked 597 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00597 $0.00597
Opus 5 $0.00298 $0.00298
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash dd916d287f69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swagger-docs-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 4d 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.

AGENTS.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

Source code lives in src/ and is organized by responsibility. source/ handles safe HTTP fetching and document discovery; navigation/ parses Knife4j links; parser/ defines parser contracts; swagger2/ implements Swagger 2.0 parsing; service/ contains client-independent query logic; server/ exposes MCP tools; and cli/ implements setup and diagnostic commands. Shared domain models are in src/domain/. Tests mirror these concerns under tests/, with reusable data in tests/fixtures/ and HTTP helpers in tests/helpers/. Compiled output belongs in dist/ and must not be edited or committed.

Build, Test, and Development Commands

  • npm ci: install the exact dependencies recorded in package-lock.json.
  • npm run dev: run the TypeScript entry point directly with tsx.
  • npm run typecheck: check strict TypeScript constraints without emitting files.
  • npm test: run the complete Vitest suite once.
  • npm run test:integration: run only the MCP integration test.
  • npm run build: compile production ESM and declarations into dist/.
  • npm run check: run type checking, all tests, and the production build; use this before a pull request. A full build is not required for every small documentation-only change.

Node.js 20 or newer is required. After building, run node dist/index.js doctor <docs-url> for a live smoke test.

Coding Style & Naming Conventions

Use strict TypeScript, two-space indentation, double quotes, semicolons, and .js extensions in relative ESM imports. Use camelCase for functions and variables, PascalCase for types and enums, and uppercase enum members. Add concise comments for status enums, non-obvious business rules, and public helper contracts. Do not add speculative compatibility fallbacks; ask when an external contract is unclear. No formatter or linter is currently configured, so follow nearby code and rely on npm run typecheck.

Testing Guidelines

Read the full file on GitHub · 30 lines

Changes

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.

  1. 4d ago First seen · 30 lines · 597 tokens per session scan A dd916d287f69

Subscribe to this mod's changes

swagger-docs-mcp AGENTS.md is an instructions file published in the GitHub repository qipeijun/swagger-docs-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 597 tokens to every session, about $0.0030 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.