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 skills add aakashg/pm-github-workflow-repo --skill prd-reviewergit clone --depth 1 https://github.com/aakashg/pm-github-workflow-repoWrote 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/aakashg/pm-github-workflow-repo/prd-reviewer)<a href="https://agentmods.dev/skills/aakashg/pm-github-workflow-repo/prd-reviewer"><img src="https://agentmods.dev/badge/skills/aakashg/pm-github-workflow-repo/prd-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aakashg/pm-github-workflow-repo/prd-reviewer"><img src="https://agentmods.dev/badge/skills/aakashg/pm-github-workflow-repo/prd-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.01279 |
| Opus 5 | $0.00019 | $0.00639 |
| Sonnet 5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
prd-reviewer 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Reviewer
Review the provided PRD against the checklist below. This is a document-completeness checklist - it asks "is each section present and specific?" It is not an eval scoring function (those score AI output and stay at 3-6 criteria; see evals/how-to-write-eval-criteria.md). For each item, output PASS or FAIL with a one-line explanation, then an overall verdict.
Checklist
Checks 1-5 apply to every PRD. Each check targets a different section, so a PRD can pass one and fail another.
- Hypothesis present and testable (Hypothesis section). A clear direction and a measurable effect. The numeric threshold itself is Check 2's job - don't fail a hypothesis here just for lacking a number. FAIL: "We will build a calendar integration." (a feature, no claimed effect) PASS: "Natural-language scheduling will reduce time-to-schedule and scheduling tickets - both measurable." (testable direction and effect)
- Success metrics have numeric thresholds (Success Metrics section). The number must appear in the Success Metrics section itself, not only restated from the hypothesis. FAIL: "Measure user engagement." PASS: "DAU increases by 12% vs control group over 4 weeks."
- Non-goals section exists and is specific. FAIL: No non-goals section. PASS: "Non-goal: Outlook integration. V1 covers Google Calendar only."
- Kill criteria defined. FAIL: No kill criteria section. PASS: "Roll back if support tickets increase by more than 5% in first 2 weeks."
- Rollout plan with ramp gates. FAIL: "Ship to all users." PASS: "10% of users for 2 weeks, 50% if metrics hold, then 100%."
AI Feature Criteria
Apply checks 6-7 only if the feature is AI-powered - i.e. a model generates, ranks, or classifies the output (chatbot, summarizer, recommender, search). If the feature is deterministic (a form, a settings toggle, a data table), skip 6-7 and note "N/A - not an AI feature."
- Behavior contract with examples. 5+ input/output examples showing expected behavior, including 2+ edge cases. FAIL: "The AI should respond helpfully." PASS: Three user queries with expected responses, one ambiguous input with fallback, one adversarial input with refusal.
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.
- 9d ago First seen · 79 lines · 39 tokens per session scan A 343bb14c804c
prd-reviewer is a skill published in the GitHub repository aakashg/pm-github-workflow-repo (3 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,279 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.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…