Borrowing it
Nothing to install: this file belongs to pipeshub-ai/mcp-server. 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/pipeshub-ai/mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/pipeshub-ai/mcp-serverWrote 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/pipeshub-ai/mcp-server/agents-md)<a href="https://agentmods.dev/instructions/pipeshub-ai/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/pipeshub-ai/mcp-server/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/pipeshub-ai/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/pipeshub-ai/mcp-server/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 | $0.00981 | $0.00981 |
| Opus 5.5 | $0.00392 | $0.00392 |
| Sonnet 5.5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — @pipeshub-ai/mcp
This file is for coding agents working in this repository. It exists so they do not invent auth set, put a PAT in QM sandbox.secretEnv, or treat QM as an MCP client.
This repository is two products in one package. The npm package is a remote MCP client library and an optional local stdio server: npx @pipeshub-ai/mcp start talks to a PipesHub instance's /mcp. The same package ships the pipeshub CLI and the QM bundle (src/cli/ and qm/). QM is an MCP server to its own harness; it cannot attach /mcp. Agents inside QM run this CLI.
Human setup is in README.md and qm/docs/use-with-qm.md. The customer-facing agent skill (install into their repo, not this one) is skills/pipeshub/SKILL.md.
Build and test
bun is required. Put it on PATH, then build, lint, and test:
export PATH="$HOME/.bun/bin:$PATH"
npm run build
npm run lint
bun test
npm run build writes bin/pipeshub.js and the MCP server. The published binary is that file, not the tsc output under esm/. CI runs bun test after lint.
Hard rules
Never print, log, echo, or commit a PAT. Compare a 6-char prefix if you must check one. Never ask anyone to paste a token into chat.
Do not ship auth set, auth import, --print-token, or any subcommand that accepts a token as an argument. The CLI reads PIPESHUB_TOKEN (then PIPESHUB_MCP_TOKEN) from the environment.
Do not put a PAT in QM sandbox.secretEnv. That variable is org-wide and would hand one person's token to everyone.
Do not invent tool.json field names. Bind to @yc-software/qm/contract types.
Do not use OAuth client_credentials. That grant has no user identity, so permission filters collapse.
Do not add PAT scopes beyond the five-scope preset to make something work. If a command needs more, stop and report — it may be unmintable. Search needs semantic:write (src/funcs/semanticSearchSearch.ts:125), not semantic:read (search history, src/hooks/oauth2scopes.ts:90-97).
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 First seen · 61 lines · 981 tokens per session scan A 74f6ed45d545
mcp-server AGENTS.md is an instructions file published in the GitHub repository pipeshub-ai/mcp-server (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 981 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
md-feedback copilot-instructions.md
Copilot instructions for yeominux/md-feedback, covering plan review workflow, before implementing any plan, annotation types and mcp setup.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.