Borrowing it
Nothing to install: this file belongs to tibuntu/renovate-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/tibuntu/renovate-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/tibuntu/renovate-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/tibuntu/renovate-mcp/claude-md)<a href="https://agentmods.dev/instructions/tibuntu/renovate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tibuntu/renovate-mcp/claude-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 | $0.04299 | $0.04299 |
| Opus 5 | $0.02150 | $0.02150 |
| Sonnet 5 | $0.00860 | $0.00860 |
| Haiku 4.5 | $0.00430 | $0.00430 |
Grade A, and why
renovate-mcp 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.
**Integration tests use stdio + fake binaries, not mocks.** `test/helpers/mcpSession.ts` spawns `dist/index.js` as a real child process and speaks JSON-RPC over stdio — so the tests exercise the actual MCP handshake and How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
MCP server that helps users design Renovate configurations interactively. TypeScript, Node ≥ 24 (aligns with Renovate's own engine requirement), built with @modelcontextprotocol/sdk 1.x, stdio transport.
Surface is intentionally small: sixteen tools (check_setup, read_config, suggest_presets, resolve_config, explain_config, resolve_config_diff, test_package_rules, preview_custom_manager, validate_config, lint_config, dry_run, dry_run_diff, annotate_dry_run, migrate_config, write_config, get_version) plus the renovate://presets resource family (namespace index, per-namespace listings, per-preset JSON). Don't grow this without a reason — the roadmap for expansion lives in the GitHub issues, not in ad-hoc additions.
Commands
npm install
npm run typecheck # tsc --noEmit (covers src + test)
npm run build # tsc -p tsconfig.build.json → dist/
npm run dev # build watch mode
npm start # run built server over stdio
npm test # vitest run (auto-builds via pretest)
npm run test:watch # vitest watch mode
npm run test:coverage # vitest run --coverage (writes coverage/ report)
npm run generate:presets # regenerate src/data/presets.generated.ts
npm run generate:managers # regenerate src/data/managers.generated.ts
npm run generate:migrations # regenerate src/data/migrations.generated.ts
Run a single test file: npx vitest run test/unit/configLocations.test.ts. Filter by name: npx vitest run -t "renovate.json5".
Two tsconfigs: the root tsconfig.json includes both src/ and test/ and is used by typecheck; tsconfig.build.json narrows to src/ only and is what build uses so tests never leak into dist/.
Architecture — the non-obvious bits
Shell out to the Renovate CLI at runtime; never import renovate as a library in src/ from the main process. Every tool that needs Renovate goes through src/lib/renovateCli.ts, which resolves the binary name (overridable via RENOVATE_BIN / RENOVATE_CONFIG_VALIDATOR_BIN env vars) and spawns it as a child process. Importing renovate from the main server process is the wrong pattern — the whole runtime design hinges on staying decoupled from Renovate's API surface. Exceptions:
- Build-time scripts under
scripts/may import Renovate to generate committed snapshots — see the preset catalogue. - Worker-thread isolation is an explicit carve-out for tools that need a Renovate library export with no CLI equivalent.
migrate_configdoes this viasrc/lib/migrationWorker.ts+src/lib/migrationWorkerImpl.ts: the main process spawns a worker on demand; the worker importsrenovate/dist/config/migration.js; the main process itself never importsrenovate. Seedocs/adrs/0001-worker-isolated-renovate-migration.mdfor the rationale.resolve_config/explain_configuse the same shape for their faithful config merge viasrc/lib/mergeWorker.ts+src/lib/mergeWorkerImpl.ts, which importrenovate/dist/config/utils.js(mergeChildConfig) in the worker (ADR-0004).test_package_rules/annotate_dry_runare the third such carve-out:src/lib/packageRulesWorker.ts+src/lib/packageRulesWorkerImpl.tsimport Renovate's real matcher registry (renovate/dist/util/package-rules/matchers.js) plusmergeChildConfig+compileand replicateapplyPackageRules' loop in the worker to recover the per-rule / per-matcher provenance Renovate exposes nowhere — seedocs/adrs/0006-worker-isolated-faithful-package-rules.md. Future tools wanting the same shape need their own ADR.
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 · 85 lines · 4,299 tokens per session scan A fc630b35e010
renovate-mcp CLAUDE.md is an instructions file published in the GitHub repository tibuntu/renovate-mcp (10 stars, last pushed 2d ago), licensed MIT. It adds 4,299 tokens to every session, about $0.0215 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 2026-08-30.
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.