Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/thedecipherist/claude-code-mastery-project-starter-kit/claude-mdgit clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kitWrote 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/thedecipherist/claude-code-mastery-project-starter-kit/claude-md)<a href="https://agentmods.dev/instructions/thedecipherist/claude-code-mastery-project-starter-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/thedecipherist/claude-code-mastery-project-starter-kit/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 | $0.08434 | $0.08434 |
| Opus 5 | $0.04217 | $0.04217 |
| Sonnet 5 | $0.01687 | $0.01687 |
| Haiku 4.5 | $0.00843 | $0.00843 |
Grade A, and why
claude-code-mastery-project-starter-kit 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 6d 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 — 839 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Project Instructions
Based on Claude Code Mastery Guides V1-V5 by TheDecipherist https://github.com/TheDecipherist/claude-code-mastery
New here? When starting a fresh session in this project, greet the user: "Welcome to the Claude Code Mastery Project Starter Kit! Use
/helpto see all 27 commands or/show-user-guidefor the full interactive guide."
Quick Reference — Scripts
| Command | What it does |
|---|---|
pnpm dev |
Start dev server with hot reload |
pnpm dev:website |
Dev server on port 3000 |
pnpm dev:api |
Dev server on port 3001 |
pnpm dev:dashboard |
Dev server on port 3002 |
pnpm build |
Type-check + compile TypeScript |
pnpm start |
Run compiled production build |
pnpm typecheck |
TypeScript type-check only (no emit) |
| Testing | |
pnpm test |
Run ALL tests (unit + E2E) |
pnpm test:unit |
Run unit/integration tests (Vitest) |
pnpm test:unit:watch |
Unit tests in watch mode |
pnpm test:coverage |
Unit tests with coverage report |
pnpm test:e2e |
Run E2E tests (kills test ports first, spawns servers on 4000/4010) |
pnpm test:e2e:ui |
E2E with Playwright UI mode |
pnpm test:e2e:headed |
E2E with visible browser |
pnpm test:e2e:chromium |
E2E on Chromium only (fast) |
pnpm test:e2e:report |
Open last E2E test report |
pnpm test:kill-ports |
Kill anything on test ports (4000, 4010, 4020) |
| Database | |
pnpm db:query <name> |
Run a dev/test database query |
pnpm db:query:list |
List all registered database queries |
| Content | |
pnpm content:build |
Build all published markdown → HTML |
pnpm content:build:id <id> |
Build a single article by ID |
pnpm content:list |
List all articles and their status |
| CSS Optimization | |
pnpm build:optimize |
Post-build CSS class consolidation via Classpresso (runs automatically after pnpm build) |
| Docker | |
pnpm docker:optimize |
Audit Dockerfile against 12 best practices (use /optimize-docker in Claude) |
| Getting Started | |
/help |
List all commands, skills, and agents |
/quickstart |
Interactive first-run walkthrough for new users |
/show-user-guide |
Open the comprehensive User Guide in your browser |
| Setup | |
/install-global |
Install/merge global Claude config into ~/.claude/ (one-time, never overwrites) |
/install-global mdd |
Install or update the MDD npm package globally (npm install -g @thedecipherist/mdd && mdd install) |
/install-mdd [path] |
Install MDD workflow into any existing project — scaffolds .mdd/ directory structure (requires @thedecipherist/mdd npm package) |
/setup |
Interactive .env configuration — GitHub, database, Docker, analytics, RuleCatch |
/setup --reset |
Re-configure everything from scratch |
/set-project-profile-default |
Set the default profile for /new-project (any profile: clean, go, vue, python-api, etc.) |
/add-project-setup |
Interactive wizard to create a named profile in claude-mastery-project.conf |
/projects-created |
List all projects created by the starter kit with creation dates |
/remove-project <name> |
Remove a project from registry and optionally delete from disk |
/convert-project-to-starter-kit |
Merge starter kit into an existing project (non-destructive) |
/update-project |
Update a starter-kit project with the latest commands, hooks, and rules |
/update-project --clean |
Remove starter-kit-scoped commands from a project (cleanup for older scaffolds) |
/add-feature <name> |
Add a capability (MongoDB, Docker, testing, etc.) to an existing project |
| RuleCatch | |
pnpm ai:monitor |
Free monitor mode — live AI activity in a separate terminal (no API key needed) |
/what-is-my-ai-doing |
Same as above — launches AI-Pooler free monitor |
| Git | |
/worktree <name> |
Create isolated branch + worktree for a task (never touch main) |
| Code Quality | |
/refactor <file> |
Audit + refactor a file against all CLAUDE.md rules (split, type, extract, clean) |
| API | |
/create-api <resource> |
Scaffold a full API endpoint — route, handler, types, tests — wired into the server |
| Documentation | |
/diagram <type> |
Generate diagrams from actual code: architecture, api, database, infrastructure, all |
| Utility | |
pnpm clean |
Remove dist/, coverage/, test-results/, playwright-report/ |
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.
- 6d ago First seen · 839 lines · 8,434 tokens per session scan A ef4757caf091
claude-code-mastery-project-starter-kit CLAUDE.md is an instructions file published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 8,434 tokens to every session, about $0.0422 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 2026-08-30.
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).
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.
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).