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/starter-kitgit 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/starter-kit)<a href="https://agentmods.dev/commands/thedecipherist/claude-code-mastery-project-starter-kit/starter-kit"><img src="https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/starter-kit.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 | $0.00025 | $0.00860 |
| Opus 5 | $0.00013 | $0.00430 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade B, and why
starter-kit 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 agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/starter-kit/version How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/starter-kit
Manage the globally installed @claude-code-mastery/starter-kit.
The kit is installed in ~/.claude/starter-kit/. Commands and skills are symlinked from there into ~/.claude/commands/ and ~/.claude/skills/, so updating the starter-kit directory instantly updates everything without needing to re-symlink.
Detect subcommand
Read the user's argument: $ARGUMENTS
update→ run Update flow belowstatus→ run Status flow belowadd→ run Add flow below- empty or unrecognised → show usage
Update flow
Check whether npm is available, then run:
npx @claude-code-mastery/starter-kit update
This overwrites ~/.claude/starter-kit/ with the latest published version, symlinks any new commands or skills that were added, and registers any new hooks in ~/.claude/settings.json.
After the command completes, report the version that is now installed:
cat ~/.claude/starter-kit/version
Tell the user: "✅ Starter kit updated to v. New commands and hooks are active immediately."
If npm / npx is not available, tell the user to install Node.js from https://nodejs.org and then run npx @claude-code-mastery/starter-kit update in their terminal.
Status flow
Check the installed version and compare with the registry:
npx @claude-code-mastery/starter-kit status
Show the output to the user as-is. If the kit is not installed, tell the user to run npx @claude-code-mastery/starter-kit init from any terminal to install it.
Add flow
Install the starter kit into the current project's .claude/ directory. This is the project-level equivalent of the global install — it gives the project its own copy of commands, hooks, and skills that Claude Code picks up automatically.
Steps:
- Check whether
~/.claude/starter-kit/exists. If not, tell the user to run the global install first:npx @claude-code-mastery/starter-kit init - Check whether
.claude/already exists in the current project:- If it does, ask the user: "
.claude/already exists in this project. Merge the starter-kit files in? Existing files with matching names will NOT be overwritten." (yes / no) - If no: stop.
- If it does, ask the user: "
- Copy from
~/.claude/starter-kit/into.claude/:
(cp -rn ~/.claude/starter-kit/commands/ .claude/commands/ cp -rn ~/.claude/starter-kit/hooks/ .claude/hooks/ cp -rn ~/.claude/starter-kit/skills/ .claude/skills/-n= no-clobber: never overwrites existing files) - If
.claude/settings.jsondoes not exist in the project, copy from the starter-kit:
If it does exist, remind the user to manually merge the hook entries fromcp ~/.claude/starter-kit/settings.json .claude/settings.json~/.claude/starter-kit/settings.jsonif needed. - Report: "✅ Starter kit added to this project's .claude/ directory. Commands and hooks are active for this project."
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 First seen · 91 lines · 25 tokens per session scan B 07ae8230a431
starter-kit 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 25 tokens to every session and 860 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
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.