Borrowing it
Nothing to install: this file belongs to jordantete/verychic-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/jordantete/verychic-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jordantete/verychic-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/jordantete/verychic-mcp/claude-md)<a href="https://agentmods.dev/instructions/jordantete/verychic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jordantete/verychic-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/jordantete/verychic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jordantete/verychic-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 | $0.01551 | $0.01551 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
verychic-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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — verychic-mcp
Unofficial, read-only, anonymous MCP server for VeryChic hotel offers.
2 tools: verychic_search_offers, verychic_offer_details
(details + availability/prices by date). Plain HTTP (curl_cffi), dual transport
(stdio + streamable-http). Not affiliated with VeryChic — see the disclaimer in README.md.
The 4 principles to apply
- Think Before Coding — make assumptions explicit; if several interpretations exist, present them (don't silently pick one); if something simpler exists, say so; if unclear, stop and ask.
- Simplicity First — minimal code that solves the problem; nothing speculative; no abstraction for a single use; if it's 200 lines for 50, rewrite.
- Surgical Changes — touch only what's needed; don't "improve" adjacent code; match the existing style; flag dead code, don't delete it; clean up only the orphans created by your own changes.
- Goal-Driven Execution — turn the task into verifiable criteria ("fix the bug" → "write a test that reproduces it, then make it pass"); short multi-step plan with per-step verification.
Commands
pip install -e ".[dev]" # install (deps: curl_cffi, mcp[cli])
pytest # offline tests (fixtures) — excludes @network
pytest -m network # real-network smoke test (hits the live API, low volume)
ruff check verychic_mcp tests # lint
verychic-mcp --help # CLI (stdio / streamable-http transports)
verychic-mcp # runs in stdio (default)
python -m build # builds the wheel (publishing)
Offline tests: they run against real JSON fixtures in tests/fixtures/
(captured in Phase 0), with no network dependency. The @network smoke test is opt-in and
excluded from CI by default (addopts = "-m 'not network'").
Architecture (one responsibility per module, independently testable)
config.py → constants: routes, PRODUCT_PARAMS, rate-limit, channelVersion fallback
errors.py → VeryChicError + CloudflareBlocked / NotFound / UpstreamError (actionable messages)
http_client.py → VeryChicClient: curl_cffi session (Chrome fingerprint), injectable rate-limit,
classify_block() maps HTTP responses to exceptions. get_json / get_text.
discovery.py → get_channel_version(): reads channelVersion from the live site, hardcoded fallback
models.py → Offer / Availability / OfferDetails dataclasses (+ offer_url, cheapest_price)
parsers.py → raw JSON → models (tolerant to missing fields via .get)
api.py → search_offers / offer_details: composes client + routes + parsers
server.py → FastMCP: registers the 2 tools, resolve_transport(), main()
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.
- 9d ago First seen · 95 lines · 1,551 tokens per session scan A 9c33fa988755
verychic-mcp CLAUDE.md is an instructions file published in the GitHub repository jordantete/verychic-mcp (1 stars, last pushed 16d ago), licensed MIT. It adds 1,551 tokens to every session, about $0.0078 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.