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/punt-labs/punt-kit/init-devgit clone --depth 1 https://github.com/punt-labs/punt-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 | $0.00010 | $0.00320 |
| Opus 5 | $0.00005 | $0.00160 |
| Sonnet 5 | $0.00002 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
init-dev 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 2d 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.
What it actually says
Punt Init (Dev)
Run the scaffolding tool from the local working tree (not the installed CLI). Use this when developing punt-kit to test changes before publishing.
Input
Project path: $ARGUMENTS (defaults to . if empty)
Process
${CLAUDE_PLUGIN_ROOT} is the repo's plugin/ subdirectory, which carries no
pyproject.toml; uv run needs the project root, hence the /.. below.
First, run detection to see what we're working with:
uv run --directory ${CLAUDE_PLUGIN_ROOT}/.. punt init --language "" $ARGUMENTS 2>&1 || true
If the output shows Language: none, ask the user which language the project
uses (python, node, swift) via AskUserQuestion, then re-run with the flag:
uv run --directory ${CLAUDE_PLUGIN_ROOT}/.. punt init --language <chosen-language> $ARGUMENTS
If a language was detected, just run:
uv run --directory ${CLAUDE_PLUGIN_ROOT}/.. punt init $ARGUMENTS
Report the output to the user. Explain what files were generated and what manual steps remain.
If the user wants contextual reconciliation, suggest /punt reconcile as the next step.
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.
- 2d ago First seen · 43 lines · 10 tokens per session scan A 1a7be388bbad
init-dev is a command published in the GitHub repository punt-labs/punt-kit (1 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 320 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 2026-08-31.
Other commands, from other repositories
meeting-listen
Play back a completed meeting summary as a voiced debate between personas.
meeting-hive
Run an autonomous PR/FAQ review meeting where four personas debate and reach consensus without user intervention.
vote
Assess whether a PR/FAQ should move forward with a structured go/no-go decision.
feedback
Incorporate feedback into PR/FAQ and redraft affected sections.
feedback-to-us
Tell us how the prfaq plugin is working for you (anonymous 1-5 feedback).
meeting
Run a simulated PR/FAQ review meeting with agentic personas.