Borrowing it
Nothing to install: this file belongs to h-mergel/bru-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/h-mergel/bru-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/h-mergel/bru-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/h-mergel/bru-mcp/agents-md)<a href="https://agentmods.dev/instructions/h-mergel/bru-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/h-mergel/bru-mcp/agents-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 | $0.01452 | $0.01452 |
| Opus 5 | $0.00726 | $0.00726 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
bru-mcp AGENTS.md scanned grade A with 1 finding 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 8d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **No shell expansion on Linux/macOS.** `spawnSync` is called with `shell: process.platform === "win32"` only. This is a deliberate security decision. How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidelines for AI coding agents working on the bru-mcp codebase.
Project overview
bru-mcp is a Model Context Protocol (MCP) server that wraps the Bruno CLI (bru) as tools for AI agents. It communicates exclusively over stdio — there are no HTTP endpoints. The server itself is a thin orchestration layer: it discovers Bruno collections on the filesystem, constructs CLI arguments, spawns the bru process, and returns the results to the MCP client.
The only external runtime dependency not bundled with the project is the bru CLI, which must be installed separately and available on PATH.
Repository structure
bru-mcp/
├── src/
│ ├── helpers.ts # Pure helper functions — no MCP dependency, fully exported and tested
│ └── index.ts # MCP server setup and all four tool definitions
├── test/
│ ├── helpers.test.ts # Unit tests using node:test (45 tests across 6 suites)
│ └── fixtures/ # Static Bruno collections used by tests
│ ├── sample-collection/ # A realistic collection with environments, folders, nested requests
│ ├── no-collection/ # Directories that should be skipped (node_modules, dist, build)
│ └── empty-dir/ # Empty directory for edge-case tests
├── dist/ # Compiled output — generated by tsc, do not edit manually
├── package.json
├── tsconfig.json
├── LICENSE
└── README.md
Key boundary: helpers.ts vs index.ts
| File | Responsibility |
|---|---|
src/helpers.ts |
All logic that can run without MCP: filesystem traversal, CLI arg construction, JSON extraction, path validation. Must be pure and exported. |
src/index.ts |
MCP server instantiation, Zod schemas, tool registration, startup check for bru. No business logic beyond wiring. |
This separation exists so that helper functions can be unit-tested without spinning up an MCP server.
Build & test commands
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.
- 8d ago First seen · 125 lines · 1,452 tokens per session scan A 346fd382f11a
bru-mcp AGENTS.md is an instructions file published in the GitHub repository h-mergel/bru-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,452 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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 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).
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.
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.