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/setupgit 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 | $0.00017 | $0.03211 |
| Opus 5 | $0.00009 | $0.01605 |
| Sonnet 5 | $0.00003 | $0.00642 |
| Haiku 4.5 | $0.00002 | $0.00321 |
Grade A, and why
setup 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Setup
Walk the user through configuring all environment variables and project settings. Creates or updates the .env file with real values while keeping .env.example as the template.
Arguments: $ARGUMENTS
If --reset is passed, start fresh (re-ask all questions even if .env already has values).
Step 0 — Check Current State
# Does .env exist?
ls .env 2>/dev/null
# Does .env.example exist?
ls .env.example 2>/dev/null
# Is .env in .gitignore?
grep -q "^\.env$" .gitignore 2>/dev/null && echo ".env is gitignored" || echo "WARNING: .env NOT in .gitignore"
If .env doesn't exist, create it from .env.example.
If .env.example doesn't exist, create a blank .env.
If .env is NOT in .gitignore, add it immediately before proceeding.
Step 0.5 — Development Environment Check (WSL)
Detect the current environment:
# Check if running on WSL
uname -r 2>/dev/null | grep -qi "microsoft\|wsl" && echo "WSL_DETECTED=true" || echo "WSL_DETECTED=false"
# Check if running on Windows (not WSL)
uname -s 2>/dev/null | grep -qi "mingw\|msys\|cygwin" && echo "WINDOWS_NATIVE=true" || echo "WINDOWS_NATIVE=false"
# Check current working directory — is the project on the Windows filesystem from WSL?
pwd | grep -q "^/mnt/c\|^/mnt/d" && echo "PROJECT_ON_WINDOWS_FS=true" || echo "PROJECT_ON_WINDOWS_FS=false"
If on Windows (native, not WSL):
Tell the user:
⚠️ You're running on Windows natively.
STRONGLY RECOMMENDED: Use WSL 2 (Windows Subsystem for Linux) instead.
Why this matters:
• HMR (hot module replacement) is 5-10x faster in WSL
• Playwright tests run significantly faster on native Linux
• File watching (nodemon, tsx watch, next dev) is dramatically more reliable
• Node.js filesystem operations avoid the NTFS translation layer
• Claude Code itself runs faster with native Linux tools (grep, find, git)
Setup (one time):
1. Open PowerShell as admin: wsl --install
2. Restart your computer
3. Install VS Code extension: "WSL" (ms-vscode-remote.remote-wsl)
4. Open VS Code → click green "><" bottom-left → "Connect to WSL"
5. Clone your projects INSIDE WSL: ~/projects/ (NOT /mnt/c/)
After setup, VS Code runs its backend inside WSL while the UI stays on Windows.
Everything just works — terminal, extensions, git, Node.js — all running natively in Linux.
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 · 338 lines · 17 tokens per session scan A 3e9811a09cdc
setup 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 17 tokens to every session and 3,211 once invoked, about $0.0001 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
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
autobot-result
Print the most recent result.md for an autobot session, so the user can see how a bot is doing without attaching to its tmux session.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
version
Show installed vs latest ai-sdlc plugin version. Bypasses the 24h SessionStart cache.
thread
Manage conversation threads (create, switch, update, delete, show).
handoff
Generate or load a session handoff. Usage: /handoff [create|resume].