Borrowing it
Nothing to install: this file belongs to railyard-sh/railyard-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/railyard-sh/railyard-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/railyard-sh/railyard-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/railyard-sh/railyard-mcp/claude-md)<a href="https://agentmods.dev/instructions/railyard-sh/railyard-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/railyard-sh/railyard-mcp/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/railyard-sh/railyard-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/railyard-sh/railyard-mcp/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 | $0.00521 | $0.00521 |
| Opus 5.5 | $0.00208 | $0.00208 |
| Sonnet 5.5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
railyard-mcp CLAUDE.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
mcp/ — the Railyard MCP server
railyard-mcp: a Model Context Protocol server (stdio) that gives an MCP client (Claude Desktop/Code,
Cursor, …) read + write access to Railyard over the REST API, authenticated with a personal access
token. TypeScript on @modelcontextprotocol/sdk.
- Source:
src/index.ts(the server + all ~31 tools),src/client.ts(the typed REST client and revision contract),src/auth.ts(hosted URL validation + explicit browser helper), andsrc/project.ts(the canonical empty project factory). The client is an accurate, compact description of the backend API. Build:npm run build(tsc→dist/); entrydist/index.js(has a shebang;bin=railyard-mcp). - Config (env vars, read in
src/index.ts):RAILYARD_TOKEN(required — ary_…PAT minted in the app under User settings → Personal access tokens),RAILYARD_BASE_URL(optional; defaults tohttps://railyard.shand is only needed for self-hosted/local backends),RAILYARD_ORG(optional default org). - Install collateral:
README.md(full tool table + copy-paste client configs),INSTALL.md(get-token → add-server → verify),manifest.json(a.mcpb/DXT desktop-extension manifest for one-click Claude Desktop install),LICENSE(MIT).
Publishing
The public package is railyard-mcp. Publishing a new version and building the .mcpb remain explicit
operator actions; never publish from an agent task without approval. Use the from-source path
(node /abs/path/railyard-mcp/dist/index.js) while validating unreleased changes.
Notes
- Project, org catalogue and org role replacements are optimistic-concurrency resources. Preserve GET
ETags and send them through
If-Match; never add an unconditional overwrite path. - Validate:
npm test+npm run test:coverage(Node 22+) +npm run typecheck+npm audit --audit-level=moderate. Don'tnpm publishwithout the operator's go-ahead.
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 · +3 lines · +16 tokens per session cf62e41157aa
- 2mo ago First seen · 29 lines · 505 tokens per session scan A b0bba231c1d0
railyard-mcp CLAUDE.md is an instructions file published in the GitHub repository railyard-sh/railyard-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 521 tokens to every session, about $0.0021 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.
railyard-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| railyard-mcp CLAUDE.mdrailyard-sh/railyard-mcp | Instructions file | 0 | 1mo ago | MIT | A | 521 | Claude Code |
| 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 |