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 skills/punt-labs/punt-kit/autonpx skills add punt-labs/punt-kit --skill autogit clone --depth 1 https://github.com/punt-labs/punt-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/skills/punt-labs/punt-kit/auto)<a href="https://agentmods.dev/skills/punt-labs/punt-kit/auto"><img src="https://agentmods.dev/badge/skills/punt-labs/punt-kit/auto.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 | $0.00015 | $0.01396 |
| Opus 5 | $0.00008 | $0.00698 |
| Sonnet 5 | $0.00003 | $0.00279 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
auto scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/punt:auto — Playbook Executor
Execute an automation playbook. Playbooks define multi-step processes as YAML files with deterministic scripts and LLM judgment steps. The executor drives each step, checks postconditions, and handles failures autonomously.
Usage
/punt:auto <playbook>— run a playbook by name/punt:auto <playbook> key=value key=value— run with parameters/punt:auto list— list available playbooks
Argument Parsing
Parse the first argument as the playbook name. Remaining arguments are
key=value parameter pairs. If list, skip to the listing behavior.
Playbook Discovery
Search for playbooks in order:
./playbooks/<name>.yaml— project-local (current working directory)${CLAUDE_PLUGIN_ROOT}/playbooks/<name>.yaml— punt-kit plugin root (when invoked as a command)../punt-kit/plugin/playbooks/<name>.yaml— org-wide fallback (when run from a sibling repo)
Project-local playbooks take precedence over org-wide playbooks with the same name.
When ${CLAUDE_PLUGIN_ROOT} is not set, skip path 2.
If a named playbook is not found in any applicable location, report every path that was searched and stop. Do not substitute a similarly-named playbook and do not improvise the steps — a playbook is a contract, and guessing at one is how a release runs the wrong phases.
For list, scan all applicable locations and print a table:
Name Source Description
───────────────────────────────────────────────────────────────────
autopilot org Autonomous bead-driven development loop
permissions-rollout org Roll out permission changes to all projects
release org Release a Punt Labs project
standards-rollout org Roll out a standards change across all projects
<name> local <description>
Execution Protocol
Phase 0: Load and Validate
- Read the YAML file.
- Extract
name,description,mode,parameters,preconditions,steps. - Validate required parameters have values (from arguments or defaults).
- If any required parameter is missing, report which ones and stop.
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 · 152 lines · 15 tokens per session scan A e672eb92f48c
auto is a skill published in the GitHub repository punt-labs/punt-kit (1 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,396 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 skills, from other repositories
prfaq
This skill should be used when the user asks to "write a PR/FAQ", "prfaq", "working backwards", "product discovery", "evaluate a product idea", "press release FAQ", "test product value", "revise prfaq", "update prfaq", "add research to prfaq", "add FAQs", "run a meeting", "review meeting", "hive meeting", "autonomous…
recall
Use find before WebSearch or WebFetch for research, or before answering a why/how/what-did-we-decide question. Quarry indexes this codebase, design docs, prior session transcripts, and previously fetched web pages — it often already has the answer. Prefer grep for symbol and value lookups; prefer find for meaning. Use…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…