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-00-pipeline-orchestratorgit 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-00-pipeline-orchestrator)<a href="https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-00-pipeline-orchestrator"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-00-pipeline-orchestrator/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-00-pipeline-orchestrator"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-00-pipeline-orchestrator.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 | $0.00088 | $0.01516 |
| Opus 5 | $0.00044 | $0.00758 |
| Sonnet 5 | $0.00018 | $0.00303 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
prd-00-pipeline-orchestrator 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Pipeline Orchestrator
Purpose
Coordinate the full workflow from rough idea to business-usable, delivery-grade PRD workspace. This skill does not write every detail itself. It decides which PRD sub-skills should be used, in what order, what artifact each stage must produce, and when a later stage must send work back for revision. Its goal is to finish the PRD, not to produce a list of reasons why the PRD is unfinished.
The core principle:
AI expands possibilities; product management compresses them into executable consensus.
Inputs
Accept any of the following:
- A rough product idea.
- A user feedback fragment.
- An operations request.
- A boss/strategy direction.
- A half-written PRD.
- A feature change proposal.
Operating rules
- Do not pretend the system context is known.
- Do not ask a long questionnaire before producing value.
- Start with a lightweight assumption map, then mark unknowns.
- Keep each stage output small enough for the next stage to consume.
- Preserve uncertainty labels:
Fact,Assumption,Decision needed,Risk,Out of scope. - Never let a draft hide uncertainty, but also do not leave solvable gaps unresolved.
- Write PRD content in Chinese by default unless the user asks for another language.
- Ask at most 3 blocking questions per stage. Continue with explicit assumptions for non-blocking unknowns.
- Each stage should create or update only its own stage artifact. Do not merge all details into the final PRD early.
- If a later stage exposes a
Rule gap, return to the relevant earlier artifact and update it before continuing. - If a stage has unresolved blocking
Decision neededitems, resolve them through the delivery loop before continuing. prd-06-admin-configmay conclude that no admin or operations config is needed for this version. Do not invent admin requirements.
Delivery loop
When a blocker appears, do not merely record it and continue. Use this loop:
- Locate the owning artifact: boundary, rules, flow, page, admin, data, or risk.
- Inspect existing artifacts and any available project context.
- Choose a conservative default when confidence is high enough for a product owner to review. Record the rationale and rejected alternative.
- Update the owning earlier artifact.
- Re-run every later stage affected by that change.
- Continue only when the downstream artifact is executable by its audience.
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.
- 11d ago First seen · 125 lines · 88 tokens per session scan A 38f5762df486
prd-00-pipeline-orchestrator is a skill published in the GitHub repository baobao2333/prd-agent-kit (5 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 1,516 once invoked, about $0.0004 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…