Borrowing it
Nothing to install: this file belongs to kardaj/openapi-tools-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kardaj/openapi-tools-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/kardaj/openapi-tools-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/kardaj/openapi-tools-mcp/agents-md)<a href="https://agentmods.dev/instructions/kardaj/openapi-tools-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kardaj/openapi-tools-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kardaj/openapi-tools-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kardaj/openapi-tools-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00353 | $0.00353 |
| Opus 5.5 | $0.00141 | $0.00141 |
| Sonnet 5.5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
openapi-tools-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 1mo 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.
What it actually says
- never use
pip. Useuv pipinstead. - keep
README.mdup to date whenever the server changes.
Design Philosophy
- MCP tools should be self-describable: generated tool descriptions, parameter schemas, README examples, and tests should tell the same story without requiring users to inspect implementation code.
- Keep the public tool surface small and flexible: prefer extending existing tools and input shapes when that preserves compatibility, and avoid adding narrowly scoped tool names unless a distinct workflow genuinely requires one.
Quality Gates
- MCP server self-documentation is part of the public API. When a change affects tool behavior, inputs, outputs, caching, errors, or supported sources, the implementation quality gate must inspect generated MCP tool metadata and verify that descriptions and parameter schemas are up to date with the shipped features. Add or update regression tests for generated tool metadata when practical.
Agent Workflow
This section is managed by agent-flow sync; do not edit it directly. Add project-specific instructions outside the agent-flow markers.
- Before making implementation changes, checking PR state, addressing PR comments, or running PR checks, run
.agent-flow/cli.sh agent prompt implementand follow its output. - For requests to change quality gates, prompts, or project knowledge, treat it as configuration work: update durable hooks in
agent-flow.configafter inspecting.agent-flow/cli.sh agent config help, validate with.agent-flow/cli.sh agent validate config --intended <path>, then run.agent-flow/cli.sh sync; durable prompt behavior lives in package templates and.agent-flow/templatesoverrides; inspect prompts with.agent-flow/cli.sh agent prompt <mode>.
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.
- 1mo ago Changed · +1 lines · +102 tokens per session e983c13e7fc2
- 2mo ago First seen · 20 lines · 251 tokens per session scan A 87e41652e1fd
openapi-tools-mcp AGENTS.md is an instructions file published in the GitHub repository kardaj/openapi-tools-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 353 tokens to every session, about $0.0014 per session on Opus 5.5. 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.
openapi-tools-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| openapi-tools-mcp AGENTS.mdkardaj/openapi-tools-mcp | Instructions file | 0 | 26d ago | MIT | A | 353 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |