Borrowing it
Nothing to install: this file belongs to ThomasCrouzet/mcp-grand-lyon. 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/ThomasCrouzet/mcp-grand-lyon/main/AGENTS.mdgit clone --depth 1 https://github.com/ThomasCrouzet/mcp-grand-lyonWrote 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/thomascrouzet/mcp-grand-lyon/agents-md)<a href="https://agentmods.dev/instructions/thomascrouzet/mcp-grand-lyon/agents-md"><img src="https://agentmods.dev/badge/instructions/thomascrouzet/mcp-grand-lyon/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/thomascrouzet/mcp-grand-lyon/agents-md"><img src="https://agentmods.dev/badge/instructions/thomascrouzet/mcp-grand-lyon/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 | $0.00696 | $0.00696 |
| Opus 5.5 | $0.00278 | $0.00278 |
| Sonnet 5.5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
mcp-grand-lyon 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grand Lyon MCP
Scope
This Go module exposes read-only Lyon mobility tools through MCP and a native CLI.
Keep MCP integration in internal/adapter/.
Keep provider access separate from models and services.
Embedded fixtures reside in internal/assets/fixtures/.
Offline process tests use temporary SQLite databases and copied fixtures.
Commands
go mod download
make lint
make test
make vulnerability
make quality combines lint, race-enabled tests, and the pinned vulnerability check.
Use temporary configuration, data, and database paths for CLI checks.
Use embedded fixtures for offline validation.
Testing policy
This policy applies to every existing and future project, including projects outside this directory. Keep these requirements when creating, importing, or revising project instructions. Use local instructions for commands, fixtures, retained failure modes, and artifact paths.
- Never write unit tests after you write code.
- Highly prefer E2E tests as the sole testing mechanism.
- Use E2E tests to verify complex features through observable results.
- At the end of each E2E run, produce a verifiable and repeatable artifact.
- Record the command, source revision, environment, fixtures, and results with the artifact.
- Include the working diff identity when the source has uncommitted changes.
- Before isolated testing, first write down all identified ways the system could fail.
- Then write the necessary tests before the implementation.
- Keep an isolated test only for a concrete failure that the E2E suite does not detect.
- Examine actual assertions, fixtures, mocks, and skips before removing a test.
- Do not treat disabled E2E tests or simulated boundaries as proof of equivalent coverage.
- Do not add tests for coverage percentages, type contracts, dependency behavior, or mocked call sequences alone.
Browser, CLI, API, and protocol E2E tests can verify observable behavior. A report, trace, exported file, or captured protocol result can provide an artifact. The artifact must include results and enough information to repeat the check. Passing isolated tests does not establish E2E success.
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.
- 7d ago Changed · +21 lines · -18 tokens per session e68beba1f1c7
- 8d ago Changed · +6 tokens per session dec7bc7ab728
- 1mo ago First seen · 48 lines · 708 tokens per session scan A bb616383466d
mcp-grand-lyon AGENTS.md is an instructions file published in the GitHub repository ThomasCrouzet/mcp-grand-lyon (0 stars, last pushed 4d ago), licensed MIT. It adds 696 tokens to every session, about $0.0028 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 2026-09-26.
Other instructions, from other repositories
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.