Borrowing it
Nothing to install: this file belongs to LeoMbm/malt-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/LeoMbm/malt-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/LeoMbm/malt-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/leombm/malt-mcp/claude-md)<a href="https://agentmods.dev/instructions/leombm/malt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/leombm/malt-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 | $0.01173 | $0.01173 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
malt-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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Philosophy
- Scraping is fragile — keep selectors isolated in
scraping/, never intools/ - One browser tab at a time — tool calls are serialized, never concurrent
- Headed mode only — Cloudflare blocks headless, don't try to work around it
- Session persistence — browser profile in
~/.malt-mcp/must survive restarts
What this project does
MCP server that lets AI assistants manage a Malt.fr freelance account via browser automation (Patchright). No API — everything is scraped from the real site.
Stack
- Patchright (not Playwright) — anti-detection fork, required for Malt/Cloudflare
- FastMCP v3 with lifespan for browser lifecycle management
uv run patchright install chromiumrequired before first use (bootstrap.py auto-runs this)- Managed Chromium stored in
~/.malt-mcp/patchright-browsers/— never uses system Chrome
Commands
uv run malt-mcp --login— manual browser login (Google OAuth broken, use email/password only)uv run mcp dev malt_mcp_server/server.py— MCP Inspector for local testinguv run ty check— type checker (runs in pre-commit, not mypy)
Architecture decisions
tools/are thin MCP wrappers: auth check → navigate → delegate toscraping/scraping/contains all DOM selectors and page interaction logic- Tools register via
register_*_tools(mcp)pattern inserver.pyto avoid circular imports constants.pyholds all Malt URLs and timeouts — never hardcode URLs elsewherecore/browser.pymanages Patchright lifecycle — BrowserManager is injected via FastMCP lifespan context- Navigation uses
wait_until="commit"—networkidlehangs because Malt SPA never stops fetching
Patterns to follow
- Every new tool: create
scraping/<name>.py+tools/<name>.py, register inserver.py - Scroll-to-load: Malt lazy-loads lists — scroll the conversation list to get all items before scraping
- Auth is checked per-tool call via
require_auth()— never assume session is valid - Raise
ToolErrorfrom tool layer, domain exceptions (MaltAuthError, etc.) from scraping/core
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 First seen · 89 lines · 1,173 tokens per session scan A c1fac2e69036
malt-mcp CLAUDE.md is an instructions file published in the GitHub repository LeoMbm/malt-mcp (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,173 tokens to every session, about $0.0059 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
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).
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.
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 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).
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.