Borrowing it
Nothing to install: this file belongs to gabry-ts/mcp-harness. 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/gabry-ts/mcp-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/gabry-ts/mcp-harnessWrote 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/gabry-ts/mcp-harness/claude-md)<a href="https://agentmods.dev/instructions/gabry-ts/mcp-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/gabry-ts/mcp-harness/claude-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/gabry-ts/mcp-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/gabry-ts/mcp-harness/claude-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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
mcp-harness CLAUDE.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.
subprocess.ts — subprocess/stdio transport mode How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-harness
In-memory testing toolkit for MCP servers in TypeScript — supertest for MCP.
Stack
- TypeScript (strict), Node.js >=18, ESM (
"type": "module") - Build: tsup (dual CJS/ESM with .d.ts)
- Test: vitest (globals: true, testTimeout: 15000)
- Format: prettier (singleQuote, trailingComma all, printWidth 100)
- Dependencies: @modelcontextprotocol/sdk (runtime), zod (dev)
Commands
npm run build— build with tsup (outputs dist/)npm run dev— build in watch modenpm test— run vitestnpm run test:watch— run vitest in watch modenpm run lint— check formatting with prettiernpm run format— fix formatting with prettiernpm run changeset— create a changesetnpm run version— version packages from changesetsnpm run release— build and publish to npm
Project Structure
src/
index.ts — main entry point, re-exports public API
assertions.ts — framework-agnostic assertion helpers
types.ts — HarnessOptions, SubprocessConfig, isSubprocessConfig
harness.ts — McpHarness class, createHarness factory
in-memory.ts — in-memory transport mode
subprocess.ts — subprocess/stdio transport mode
test/
in-memory.test.ts — in-memory mode tests
subprocess.test.ts — subprocess mode tests
lifecycle.test.ts — close/timeout tests
assertions.test.ts — assertion helper unit tests
edge-cases.test.ts — edge case tests
fixtures/
echo-server.ts — tool/resource/prompt test fixture
error-server.ts — error scenario fixture
slow-server.ts — timeout test fixture
env-server.ts — env/cwd test fixture
examples/
vitest-example/ — Vitest usage example
jest-example/ — Jest usage example
standalone-example/ — node:assert usage example
Conventions
- Entry points: src/index.ts (main), src/assertions.ts (assertion helpers)
- Exports map:
.and./assertionswith dual ESM/CJS + types - tsup outputs
.js(ESM) and.cjs(CJS) — not.mjs - Local imports require
.jsextension (Node16 module resolution) - Test fixtures in test/fixtures/
- Examples in examples/
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 · 56 lines · 555 tokens per session scan A df0a75356510
mcp-harness CLAUDE.md is an instructions file published in the GitHub repository gabry-ts/mcp-harness (2 stars, last pushed 2mo ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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.