Borrowing it
Nothing to install: this file belongs to samiashi/chrono24-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/samiashi/chrono24-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/samiashi/chrono24-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/samiashi/chrono24-mcp/agents-md)<a href="https://agentmods.dev/instructions/samiashi/chrono24-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/samiashi/chrono24-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 | $0.02872 | $0.02872 |
| Opus 5 | $0.01436 | $0.01436 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
chrono24-mcp 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository.
What this is
An MCP server (chrono24-mcp) exposing Chrono24 watch-marketplace tools to LLM clients over stdio. There is no official Chrono24 API; all data comes from scraping Chrono24's website through a real browser to pass their Cloudflare managed challenge. TypeScript, official MCP SDK, zod schemas, cheerio parsers.
Commands
npm ci # install exactly per lockfile
npm run build # tsc -> build/
npm run typecheck # tsc --noEmit
npm run lint # eslint (flat config in eslint.config.js)
npm run format # prettier --write .
npm test # vitest, offline parser tests against test/fixtures/*.html (safe for CI)
npm run smoke # LIVE end-to-end test: spawns server, lists tools, searches, fetches detail (needs Google Chrome; hits chrono24.com)
npm run capture-fixtures # LIVE: refresh test/fixtures by re-fetching brand/search/detail pages
node build/index.js # run the server manually on stdio
Before committing run npm run format && npm run lint && npm run typecheck && npm test - CI (.github/workflows/ci.yml) runs exactly those plus build. Prettier config: 110 print width, double quotes, trailing commas. ESLint: typescript-eslint recommended + prettier compat; empty catch blocks are allowed.
Smoke overrides for testing a published package instead of the local build:
SMOKE_COMMAND=npx SMOKE_ARGS='["-y","chrono24-mcp@latest"]' SMOKE_CWD=/tmp npm run smoke
Do NOT add live-network tests to CI: GitHub runners' IPs are blocked by Cloudflare. Parser tests use recorded HTML fixtures in test/fixtures/.
Architecture
src/index.ts MCP server entry: registers 25 tools + 3 prompts, zero-result query hints, spread-sampling degradation via registerTool/registerPrompt (readOnlyHint annotations, output schemas + structuredContent), parsed-result caching, not-found detection, disk-persisted taxonomy, graceful shutdown (signals + stdin close)
src/fetcher.ts Playwright-core fetcher: strict request serialization (createSerializer mutex - concurrent MCP tool calls share one page), persistent Chrome profile, memoized launch, crash recovery via context close listener, status-aware challenge sniffing, warmup-on-demand retry, politeness delay, stale SingletonLock recovery, in-page fetchJson for same-origin JSON APIs
src/parsers/search.ts Search URL builder + listing-card parser (current markup era), facet param allowlist, locale-aware price parsing (parseLocalizedNumber)
src/parsers/detail.ts Detail page parser: schema.org Product JSON-LD + spec table; hasDetailContent detects removed listings
src/parsers/taxonomy.ts Brand list (manufacturerIds select), model catalog (--mod links), facet selects, drift warnings
src/parsers/ratings.ts Dealer ratings JSON normalizer (totals, filteredTotal, star filters)
src/parsers/stats.ts Price percentile stats (computeStats) + rank-interpolated population estimates (estimateStats)
src/parsers/guide.ts Model-page editorial guide parser: h3 sections + per-reference price table (static SEO content)
src/cache.ts TTL + LRU cache (default 200 entries; search 180s, detail 1800s, taxonomy 86400s) - stores parsed payloads, never raw HTML
src/diskStore.ts Generic keyed JSON disk cache (taxonomy, per-brand models, probed UA - all inside the profile dir)
src/config.ts Env-var config (numeric envs validated via numFrom; garbage falls back to defaults)
src/tools/schemas.ts Zod input AND output schemas (single source of truth for tool contracts)
test/parsers.test.ts Offline vitest suite over recorded fixtures - keep green, extend when parsers change
test/cache.test.ts TTL/LRU cache behavior
test/fetcher.test.ts Serializer (request mutex) behavior
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.
- 2d ago Changed · +19 lines · +1,365 tokens per session 9a2b04ac5772
- 6d ago First seen · 78 lines · 1,507 tokens per session scan A 2651c38931db
chrono24-mcp AGENTS.md is an instructions file published in the GitHub repository samiashi/chrono24-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 2,872 tokens to every session, about $0.0144 per session on Opus 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.
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.