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/zhpeng24/devkit/github-product-managernpx skills add zhpeng24/devkit --skill github-product-managergit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00035 | $0.00746 |
| Opus 5 | $0.00017 | $0.00373 |
| Sonnet 5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
github-product-manager 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Goal Discovery
Turn product intent into a SIES Goal Contract and, when authorized, a GitHub Issue. The purpose is to close decisions that matter, not to complete a fixed questionnaire.
This skill does not design architecture or implement code.
Start With Existing Evidence
Read only the context needed to understand the request:
- user-provided goals and examples;
- relevant README, product docs, code paths, issues, and recent decisions;
- existing Goal Contract, if one already exists.
Do not scan the whole repository, list every PR, or ask the user to reconfirm facts that are already reliable. Summarize assumptions only when a wrong assumption would change scope or success.
Build the Decision Map
Read references/question-framework.md. Classify each Goal Contract field as:
- known — supported by the request or repository evidence;
- safe assumption — low-impact and reversible; state it briefly;
- blocking unknown — the answer changes outcome, scope, evaluation, or an irreversible action.
Ask one concise question only for a blocking unknown. If the contract is already evaluable, draft it immediately.
Goal Contract
Read references/issue-template.md and capture:
- Outcome and affected users or systems;
- success signals;
- non-goals and MVP boundary;
- constraints and impact;
- key uncertainties;
- Evaluation Contract: decision, evidence, and pass/fail/stop conditions.
Success signals must be observable but do not all need to be automated tests. Use user scenarios, runtime behavior, metrics, visual evidence, contracts, or tests according to the goal.
Choose the Next Artifact
| Current state | Next artifact |
|---|---|
| Goal is clear and Engineering can start | Product Goal / Engineering Issue |
| A product or technical assumption still dominates risk | Exploration or Prototype Issue |
| Evidence is already sufficient | Decision record or implementation handoff |
| Outcome is not worth pursuing | Stop decision; do not manufacture an Issue |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 95 lines · 35 tokens per session scan A 5e51aaa1ca7f
github-product-manager is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 746 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…