What is init-claude-md?

A workflow that creates a project-specific CLAUDE.md file for a pulled Rossum prd2 project. CLAUDE.md is a project instruction file that Claude Code reads automatically in future sessions.

Inspecting a local project and documenting its environments, queues, hooks, schemas, integration targets, commands, and editing or deployment rules.

It records the project's Rossum conventions and structure so future sessions do not have to rediscover how files, commands, environments, and deployment approvals work.

init-claude-md — Skill for Claude Code by rossumai

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add rossumai/claude-marketplace

Claude Code

/plugin install rossum-sa

Made for: Claude Code.

Or install rossum-sa, the plugin that ships this one along with the rest of its 33 skills, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/init-claude-md/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/init-claude-md)

Your own site

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/init-claude-md"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/init-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/init-claude-md"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/init-claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,763 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00107	$0.02763
Opus 5	$0.00053	$0.01381
Sonnet 5	$0.00021	$0.00553
Haiku 4.5	$0.00011	$0.00276

Measured 12d ago against content hash dceac425fbd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

init-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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (inspect.py, tests/fixtures/coupa/dev-env/hooks/coupa_export/code.py, tests/fixtures/sap/dev-env/hooks/sap_idoc_export/code.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/rossum-sa/skills/init-claude-md/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize CLAUDE.md for a Rossum prd2 Project

Path or context: $ARGUMENTS

What this skill does

Generates a CLAUDE.md at the root of a pulled prd2 project so future Claude Code sessions know it's a Rossum implementation and apply the right safety rules (edit .py not JSON, never push/deploy without approval, MDH targets are enums).

The auto-generated portion is wrapped in  markers. Re-running this skill rewrites only the marked block; the "Project-Specific Notes" section below the markers is preserved.

Why a project-specific CLAUDE.md

Anthropic recommends CLAUDE.md for project memory — it is auto-loaded at the start of each Claude Code session. Without one, every session has to rediscover Rossum conventions (edit .py not JSON, prd2 commands, safety rules, where queues/hooks/formulas live). A pre-filled file removes that friction.

Best-practices sections (from the source article that motivated this skill):

Project Overview — what the implementation is, what it optimizes for
Tech Stack — explicit list of what's in use and what to avoid
Architecture — real directory layout, where new things go
Coding Conventions — hard rules (not vague "write clean code")
Commands — exact commands, not paraphrases
Safety Rules — confirmation gates for destructive ops
File Placement Rules — when to create new files vs. edit existing
Testing & Quality — how "done" is validated
Recommended Skills — pointers to relevant rossum-sa:* skills
Project-Specific Notes — human-curated area

Workflow

Step 1: Resolve the project directory

If $ARGUMENTS is a path, use it. Otherwise use the current working directory. Pass this directory straight to the inspector (Step 2) — the inspector detects the deployment tool via its marker file and decides whether the project is supported, so don't pre-gate on specific files here. (The single "not supported" stop lives in Step 2.)

Step 2: Run the inspector

Read the full file on GitHub · 150 lines

Files

What ships with it

26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 150 lines · 107 tokens per session scan A dceac425fbd3

Subscribe to this mod's changes

init-claude-md is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 2,763 once invoked, about $0.0005 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens