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 commands/thedecipherist/claude-code-mastery-project-starter-kit/helpgit clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kitWhat 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 | $0.00006 | $0.01300 |
| Opus 5 | $0.00003 | $0.00650 |
| Sonnet 5 | $0.00001 | $0.00260 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
help 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 3d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help — All Available Commands
Display the complete list of commands and skills available in this project.
Step 1 — Detect Context
Determine if we're running inside the starter kit or a scaffolded project:
- Check if BOTH
claude-mastery-project.confAND.claude/commands/new-project.mdexist in the project root- Yes → This is the starter kit. Show ALL commands (both
scope: projectandscope: starter-kit), grouped with a "KIT MANAGEMENT" section. - No → This is a scaffolded project. Show only the commands present in
.claude/commands/.
- Yes → This is the starter kit. Show ALL commands (both
Step 2 — Enumerate Commands
- Glob
.claude/commands/*.mdto find all command files - For each file, read the YAML frontmatter to extract:
description— the command descriptionscope—projectorstarter-kit(if present)
- Build the command list dynamically from what's actually installed
Step 3 — Display
Format the output as a grouped reference. Use the categories below for organization.
If Starter Kit (show all commands with KIT MANAGEMENT section):
=== Claude Code Starter Kit — Command Reference ({N} commands) ===
GETTING STARTED
/help List all commands and skills (this screen)
/quickstart Interactive first-run walkthrough for new users
/install-global Install/merge global Claude config into ~/.claude/
/setup Interactive .env configuration — GitHub, database, Docker, analytics
/setup --reset Re-configure everything from scratch
/show-user-guide Open the comprehensive User Guide in your browser
KIT MANAGEMENT (starter kit only — not copied to projects)
/new-project Scaffold a new project from a profile (clean, default, api, go, vue, python-api, etc.)
/set-project-profile-default Set the default profile for /new-project (any profile name)
/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 Remove a project from the registry and optionally delete it 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
CODE QUALITY
/review Systematic code review against 7-point checklist
/refactor <file> Audit + refactor a file against all CLAUDE.md rules
/security-check Scan project for secrets, vulnerabilities, and .gitignore gaps
/commit Smart commit with conventional commit format
DEVELOPMENT
/create-api <res> Scaffold a full API endpoint — route, handler, types, tests
/create-e2e <feat> Generate Playwright E2E test with explicit success criteria
/test-plan Generate a structured test plan for a feature
/progress Check project status — files, tests, git activity, next actions
INFRASTRUCTURE
/diagram <type> Generate diagrams from code: architecture, api, database, infrastructure, all
/architecture Display system architecture and data flow
/optimize-docker Audit Dockerfile against 12 production best practices
/worktree <name> Create isolated branch + worktree for a task
MONITORING
/what-is-my-ai-doing Live monitor of AI activity — tokens, cost, violations
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.
- 3d ago First seen · 121 lines · 6 tokens per session scan A ccb5d9e086ce
help is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 1,300 once invoked, about $0.0000 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.