Borrowing it
Nothing to install: this file belongs to protomated/protomated-plugins-official. 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/protomated/protomated-plugins-official/main/CLAUDE.mdgit clone --depth 1 https://github.com/protomated/protomated-plugins-officialWrote 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/protomated/protomated-plugins-official/claude-md)<a href="https://agentmods.dev/instructions/protomated/protomated-plugins-official/claude-md"><img src="https://agentmods.dev/badge/instructions/protomated/protomated-plugins-official/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/protomated/protomated-plugins-official/claude-md"><img src="https://agentmods.dev/badge/instructions/protomated/protomated-plugins-official/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 | $0.03596 | $0.03596 |
| Opus 5.5 | $0.01438 | $0.01438 |
| Sonnet 5.5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade B, and why
protomated-plugins-official CLAUDE.md scanned grade B 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 4d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- The root `.mcp.json` is a local development MCP config (unrelated to the plugins) and must not contain committed credentials — keep tokens in env vars or gitignore the file. How it starts
The opening of the file, as written. The whole thing — 166 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 repo is
A Claude plugin marketplace for solo attorneys, modeled on anthropics/claude-for-legal. It ships one flagship bundle (the Solo Attorney Starter Kit — six skills, per the original CP1 spec: none of the six are also standalone plugins — the Starter Kit's own release is their release), the Legal Billing Tracker (a separate product with its own remote MCP server), four further standalone, single-skill, connector-free plugins (Demand Letter Drafter, Estate Planning Document Assembler, Immigration Filing Drafter, Contract Document Reviewer) that each mirror their own upstream product repo, three more connector-free plugins (Bar-Compliant Marketing Reviewer, Conflict-of-Interest Checker, Spanish Intake Skill) built natively in this repo from the CP-catalog (docs/planned-plugins.json) rather than mirroring an external upstream repo, and two further standalone, single-skill plugins (Flat-Fee Repricing Calculator, Research Memo Drafter) that each mirror their own upstream product repo and ship only as their own standalone plugin, not inside the starter kit at all — neither is a CP1 component skill, and each uses the Claude Filesystem connector (optional for Flat-Fee Repricing Calculator, central to Research Memo Drafter's own workflow). There is no runtime code for the drafting skills, no bundled MCP server, and no backend beyond the Legal Billing Tracker's own hosted service. The product is mostly content: markdown skill files, JSON manifests, and a Next.js landing page.
Repo layout
.claude-plugin/marketplace.json Marketplace manifest — every installable plugin, in curated order
solo-attorney-starter-kit/ Flagship bundle (all six bundled skills; also packaged into the release .zip)
.claude-plugin/plugin.json Identity manifest (kebab-case name, semver version)
(no .mcp.json) Removed — Gmail/Calendar/Filesystem are optional on Claude
(Settings → Connectors) and don't exist on ChatGPT Desktop at
all; every skill already degrades to paste/attach without them,
and ChatGPT's plugin importer rejects any zip containing a
.mcp.json. See the "Notes" section below.
prompts/system-prompt.md Master system prompt — ethical guardrails live here
skills/*/SKILL.md One directory per skill; YAML frontmatter + markdown body.
None of these six skills also ship as a standalone plugin.
flat-fee-calculator/ Standalone plugins, one skill each, each mirroring its own
research-memo-drafter/ upstream product repo (protomated/claude-flat-fee-calculator,
protomated/claude-research-memo-drafter): .claude-plugin/
plugin.json, CONNECTORS.md, prompts/system-prompt.md,
README.md, skills/<skill-name>/SKILL.md. Both use the
Filesystem connector (optional for flat-fee-calculator, so
it's documented in prose only, no .mcp.json; central to
research-memo-drafter's workflow, so it has one). Neither is
a CP1 component skill, so neither lives in the Starter Kit.
legal-billing-tracker/ Standalone plugin (plugin.json name: legal-billing) — a
separate product, not split from the starter kit. Uses a
hosted remote MCP server instead of blank-url connectors.
demand-letter-drafter/ Standalone, connector-free plugins — one skill each,
estate-planning-document-assembler/ each mirroring its own upstream product repo. No
immigration-filing-drafter/ .mcp.json file at all (not generated by
contract-document-reviewer/ write-mcp-configs.mjs): these skills read only a
workspace folder the attorney explicitly attaches —
no MCP connector or auth step, so there's nothing to
declare.
bar-compliant-marketing-reviewer/ Same connector-free layout, but built natively here
conflict-of-interest-checker/ from the CP-catalog — no upstream repo to re-sync from.
spanish-intake-skill/
site/ Next.js landing page (Cloudflare Pages)
app/api/subscribe/route.ts Edge route: email capture → Kit API
scripts/
validate-plugin.mjs Validates marketplace.json + every listed plugin
write-mcp-configs.mjs Regenerates each plugin's .mcp.json (source of truth for connectors)
release-check.mjs Preflight for `npm run release`
docs/ Technical spec + planned-plugins.json (unbuilt catalog entries)
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.
- 4d ago Changed · +5 lines · +348 tokens per session 995f405678d4
- 12d ago Changed · +5 lines · +163 tokens per session 11b808504acc
- 21d ago Changed · +1 lines · +68 tokens per session 4fbdbd1b73cc
- 1mo ago Changed · +4 lines · +264 tokens per session d54896780825
- 1mo ago First seen · 151 lines · 2,753 tokens per session scan B 82923187e2b5
protomated-plugins-official CLAUDE.md is an instructions file published in the GitHub repository protomated/protomated-plugins-official (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,596 tokens to every session, about $0.0144 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.