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/new-projectgit 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/commands/thedecipherist/claude-code-mastery-project-starter-kit/new-project)<a href="https://agentmods.dev/commands/thedecipherist/claude-code-mastery-project-starter-kit/new-project"><img src="https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/new-project.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 | $0.00010 | $0.02975 |
| Opus 5 | $0.00005 | $0.01488 |
| Sonnet 5 | $0.00002 | $0.00595 |
| Haiku 4.5 | $0.00001 | $0.00298 |
Grade B, and why
new-project 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 5d 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 agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- If yes: copy `global-claude-md/CLAUDE.md` → `~/.claude/CLAUDE.md` and `global-claude-md/settings.json` → `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project Scaffold
Create a new project with all best practices from the Claude Code Mastery Guides.
Arguments: $ARGUMENTS
Argument Parsing
Step 0 — Read the config file
Before parsing arguments, read claude-mastery-project.conf (in the starter kit root or ~/.claude/claude-mastery-project.conf as fallback).
Extract the [global] section for root_dir and default_profile.
root_dir— Default parent directory for new projectsdefault_profile— Profile to use when no profile is specified in arguments (e.g.,default_profile = clean). If not set, ask the user as before.
Step 0.0 — Global Claude Config (one-time setup)
Check if the user already has the global Claude config installed:
# Check if global CLAUDE.md exists
ls ~/.claude/CLAUDE.md 2>/dev/null
If ~/.claude/CLAUDE.md does NOT exist:
- ASK: "You don't have a global CLAUDE.md yet. Want me to install the Claude Code Mastery global config to
~/.claude/? This sets up security rules, hooks, and standards that apply to ALL your projects. (This is a one-time setup.)" - If yes: copy
global-claude-md/CLAUDE.md→~/.claude/CLAUDE.mdandglobal-claude-md/settings.json→~/.claude/settings.json - Also copy hooks:
mkdir -p ~/.claude/hooks && cp .claude/hooks/verify-no-secrets.sh ~/.claude/hooks/
If ~/.claude/CLAUDE.md DOES exist:
- ASK: "You already have a global CLAUDE.md. Want me to check if the starter kit version has anything new to merge in?"
- If yes: diff the two files and show what's different. Let the user decide what to merge.
- If no: skip and continue.
This step typically only happens once. After the first install, the global config persists across all projects.
Step 0.1 — Resolve the project path
The first argument is the project name or path. Resolve it using root_dir:
- Explicit path (starts with
./,../,~/, or/) → use as-is/new-project ~/code/my-app→ creates at~/code/my-app/new-project ./my-app→ creates at./my-app
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.
- 5d ago First seen · 245 lines · 10 tokens per session scan B 0deaceb2c1b5
new-project 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 10 tokens to every session and 2,975 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.