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/rawveg/openapi-directory-mcp/claude-mdgit clone --depth 1 https://github.com/rawveg/openapi-directory-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/rawveg/openapi-directory-mcp/claude-md)<a href="https://agentmods.dev/instructions/rawveg/openapi-directory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rawveg/openapi-directory-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 | $0.01556 | $0.01556 |
| Opus 5 | $0.00778 | $0.00778 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
openapi-directory-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories β prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β 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.
How it starts
The opening of the file, as written. The whole thing β 176 lines β stays where its author put it; the contents beside it link to each section on GitHub.
Claude Assistant Guidelines for openapi-directory-mcp
π¨ HARD RULES - WRITTEN IN STONE
GIT POLICY
NEVER PERFORM GIT OPERATIONS UNLESS EXPLICITLY TOLD TO DO SO BY THE USER
- DO NOT use
git commitunder any circumstances without explicit user instruction - DO NOT use
git addto stage changes unless explicitly told to do so - DO NOT assume when commits should be made or how files should be grouped
- MAKE CHANGES TO FILES, but let the user handle all git operations
- ALWAYS wait for explicit git instruction: "stage these files", "commit this", etc.
- This rule applies to ALL situations: bug fixes, linting fixes, feature additions, documentation updates
Why No Auto-Staging:
- User may want to use changelists
- User may want strategic commit groupings
- User may want to review changes before staging
- User may have specific staging workflows
- Staging is part of the user's approval process
Git Operations Allowed Without Permission:
git status- checking repository status (for information only)git diff- viewing changes (for information only)git log- viewing commit history (for information only)
Git Operations FORBIDDEN Without Explicit Permission:
git add- NEVER stage files without explicit instructiongit commit- NEVER without explicit instructiongit push- NEVER without explicit instructiongit merge- NEVER without explicit instructiongit rebase- NEVER without explicit instruction
Correct Workflow:
- User asks me to fix issues
- I make the file changes
- I report what was changed
- User decides how to stage and commit
π€ COLLABORATION PRINCIPLES
BE A THINKING PARTNER, NOT JUST AN EXECUTOR
Always Raise Concerns:
- If I notice edge cases the user might not have considered
- If a request might conflict with established patterns or architecture
- If there are potential rollback/deployment/maintenance implications
- If I see a better approach or alternative solution
- If the implementation might mask underlying issues
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.
- 4d ago First seen Β· 176 lines Β· 1,556 tokens per session scan A 7d238ee25253
openapi-directory-mcp CLAUDE.md is an instructions file published in the GitHub repository rawveg/openapi-directory-mcp (9 stars, last pushed 10mo ago), licensed MIT. It adds 1,556 tokens to every session, about $0.0078 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
rosetta AGENTS.md
AGENTS.md instructions for griddynamics/rosetta: Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - whenβ¦
sample-well-architected-skills-and-steering copilot-instructions.md
Copilot instructions for aws-samples/sample-well-architected-skills-and-steering, covering well-architected framework, role, when to apply, pillars and design principles.
toon-memory AGENTS.md
Instructions for LuiggiVal08/toon-memory, covering agents.md, build & verify, architecture, smarter memory pattern and visual memory pattern.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare β claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
margaret AGENTS.md
Instructions for sofiahernandes/margaret: You're a principal engineer who sizes builds to the actual requirement, not the one someone might need later. Clean falls out of good design; it isn't a separate pass.
mcp-air AGENTS.md
AGENTS.md instructions for VericyIO/mcp-air, covering agents.md, verification commands, node version, publishing and constants sync.