claude-marketplace: Instructions file for Claude Code

CLAUDE.md

claude-marketplace CLAUDE.md is an instructions file for Claude Code from rossumai/claude-marketplace. It costs 1,646 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code, an AI coding assistant, working on a Claude plugin marketplace for Rossum.ai workflows. They describe the marketplace structure, its Rossum-specific plugin, tests, and continuous integration checks.

In plain words
What is it for?
Use them when developing or reviewing this repository, especially when adding plugins or skills, changing the Rossum API server, updating documentation, or running tests and CI.
Why use it?
They give the coding assistant the project’s layout and rules before it changes code. This reduces incorrect edits to plugins, skills, the MCP server, and documentation.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is rossumai/claude-marketplace's own configuration. It tells Claude Code how to work on claude-marketplace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-marketplace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rossumai/claude-marketplace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rossumai/claude-marketplace/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rossumai/claude-marketplace

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-marketplace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rossumai/claude-marketplace/claude-md/github.svg)](https://agentmods.dev/instructions/rossumai/claude-marketplace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rossumai/claude-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/rossumai/claude-marketplace/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.

agentmods 80×15 button for claude-marketplace CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rossumai/claude-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/rossumai/claude-marketplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,646 This file is loaded in full into every session.
When invoked 1,646 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01646 $0.01646
Opus 5 $0.00823 $0.00823
Sonnet 5 $0.00329 $0.00329
Haiku 4.5 $0.00165 $0.00165

Measured 7d ago against content hash 6fc719abff66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-marketplace 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Single-file Python, zero external dependencies (stdlib `urllib` + optional `certifi` for SSL) — the `tests/test_runtime_contract.py` guard enforces the stdlib-only contract
CLAUDE.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 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.

What this is

A Claude Code plugin marketplace for Rossum.ai workflows (https://code.claude.com/docs/en/plugin-marketplaces). Ships one plugin:

  • rossum-sa — Skills, reference packs, and an MCP server for Rossum SA work

Architecture

MarketplacePluginsSkills + MCP servers

  • .claude-plugin/marketplace.json lists available plugins
  • Each plugin lives under plugins/<name>/ with its own .claude-plugin/plugin.json
  • Skills are Markdown files at plugins/<name>/skills/<skill-name>/SKILL.md
  • The rossum-sa plugin ships invocable skills (analyze, dead-code, document, implement, etc.) plus autoloaded *-reference reference packs (user-invocable: false). README.md is the authoritative list and count — the CI doc-sync guard keeps it accurate, so don't hardcode counts here.

MCP server (plugins/rossum-sa/mcp-servers/rossum-api/server.py):

  • Single-file Python, zero external dependencies (stdlib urllib + optional certifi for SSL) — the tests/test_runtime_contract.py guard enforces the stdlib-only contract
  • Implements MCP JSON-RPC over stdio (reads/writes newline-delimited JSON on stdin/stdout)
  • Tools are registered via the @_tool decorator which populates TOOLS and HANDLERS dicts
  • Three annotation levels control permission prompts: _READ_ONLY, _WRITE, _DESTRUCTIVE
  • Manages its own auth state (_cached_token, _cached_base_url) — no persistent credentials
  • All Rossum API calls go through _http_request() which handles auth, errors, and 401 invalidation
  • Pagination is handled by _paginate() for list endpoints and _rossum_list() wrapper

Tests & CI

  • .github/workflows/ci.yml runs ruff (real-errors-only) + pytest on Python 3.12 and 3.14 for every PR and push to main.
  • Run locally with pip install -r requirements-dev.txt && pytest.
  • Repo-level guard tests live in tests/: test_manifests.py (manifests parse, every SKILL.md has frontmatter), test_doc_sync.py (README headline + skills table match the filesystem; plugin/server versions match), test_runtime_contract.py (server stays stdlib-only), test_parts.py (the parts library: metadata schema, «param»↔placeholder parity, and each fragment.* parses once its seams are filled). Per-skill suites live under plugins/.../skills/<name>/tests/.
  • Part fragments are «param» templates, not runnable source — the guillemet seams are deliberately invalid in every target language, so parts/** is excluded from ruff (see pyproject.toml). Fragment syntax is checked by test_parts.py against the filled-in form, not the linter. Any new lint/validate step must also exclude parts/**.
  • The doc-sync and version guards mechanize the two sync rules below — if you add/rename a skill or tool, the guard fails until README is updated in the same change.
  • Per-skill script suites follow the testing bar in docs/testing-skill-scripts.md — scale to blast radius, pin behavior not implementation, prune in the same PR that grows a suite past the bar.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 7d ago Changed · +2 lines · +577 tokens per session 6fc719abff66
  2. 11d ago First seen · 44 lines · 1,069 tokens per session scan A 1de1dbaf98cc

Subscribe to this mod's changes

claude-marketplace CLAUDE.md is an instructions file published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It adds 1,646 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens