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 baobao2333/prd-agent-kit --skill prd-09-prd-compressorgit clone --depth 1 https://github.com/baobao2333/prd-agent-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/baobao2333/prd-agent-kit/prd-09-prd-compressor)<a href="https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-09-prd-compressor"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-09-prd-compressor/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/baobao2333/prd-agent-kit/prd-09-prd-compressor"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-09-prd-compressor.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 | $0.00047 | $0.01360 |
| Opus 5 | $0.00023 | $0.00680 |
| Sonnet 5 | $0.00009 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
prd-09-prd-compressor 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Compressor
Purpose
Turn resolved stage artifacts into a final PRD document that is short enough to review and precise enough to execute.
This skill must compress, not expand.
Invocation gate
Run this skill only when all of these are true:
- Blocking product, data, technical, legal, cost, rule, and acceptance gates are resolved.
- Remaining sign-off notes have recommended defaults and do not block engineering estimation or QA case writing.
- The risk review does not require a loop-back to an earlier artifact.
If blockers remain, do not write 08-delivery-prd.md. Return to the owning earlier skill, resolve the gap, and re-run affected later stages. Ask the user only when the missing decision cannot be responsibly made by the agent.
Inputs
- Intake brief.
- Business boundary.
- Rule model.
- Flow model.
- Page interaction spec.
- Admin config spec.
- Data and acceptance spec.
- Risk and debt review.
Compression rules
- Preserve decisions; remove brainstorming.
- Preserve rules; remove slogans.
- Preserve boundaries; remove speculative future features.
- Preserve non-blocking assumptions and sign-off notes; do not fake certainty.
- Move non-blocking details to appendix or later version.
- Convert vague wording into explicit product language.
- If a section is not actionable by engineering, design, QA, operations, or PM, delete or rewrite it.
- Do not convert unresolved
Decision needed,Rule gap, orNeeds history checkitems into final decisions. Resolve them before this skill runs, or keep only non-blocking sign-off notes with recommended defaults. - If a blocking decision remains, stop and loop back instead of compressing.
- Always include a prose feature description before goals, scope, metrics, or risk tables. This section is the product behavior spine of the PRD; do not replace it with tables.
Feature description rules
The final PRD must include a continuous natural-language description of the feature behavior. It should answer, in prose:
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 · 182 lines · 47 tokens per session scan A fe8e32c5cd65
prd-09-prd-compressor is a skill published in the GitHub repository baobao2333/prd-agent-kit (5 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 1,360 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…