Borrowing it
Nothing to install: this file belongs to karlng279/ai-ready-product-workflow-v2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/karlng279/ai-ready-product-workflow-v2/main/.claude/commands/po-pipeline.mdgit clone --depth 1 https://github.com/karlng279/ai-ready-product-workflow-v2Wrote 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/commands/karlng279/ai-ready-product-workflow-v2/po-pipeline)<a href="https://agentmods.dev/commands/karlng279/ai-ready-product-workflow-v2/po-pipeline"><img src="https://agentmods.dev/badge/commands/karlng279/ai-ready-product-workflow-v2/po-pipeline/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/commands/karlng279/ai-ready-product-workflow-v2/po-pipeline"><img src="https://agentmods.dev/badge/commands/karlng279/ai-ready-product-workflow-v2/po-pipeline.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 | $0.00000 | $0.01151 |
| Opus 5 | $0.00000 | $0.00575 |
| Sonnet 5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
po-pipeline 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 12d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/po-pipeline
Run the full PO pipeline for a feature: Brief → PRD → USM → USL → USD → UAT.
Usage
/po-pipeline [feature-name] [brief or description]
If feature-name is omitted, ask for it before starting. If a brief is provided inline, use it directly. If not, ask the user to paste or describe the feature.
What This Command Does
Executes the 5-stage PO artifact pipeline in sequence for a single feature. Each stage produces a traceable artifact stored in features/{feature-name}/po/.
| Stage | Skill | Input | Output |
|---|---|---|---|
| 1 | po-brief-to-prd |
Feature brief | prd.md |
| 2 | po-prd-to-usm |
prd.md |
usm.md |
| 3 | po-usm-to-usl |
usm.md |
usl.md |
| 4 | po-usl-to-usd |
usl.md |
usd/ST-XXX.md per story |
| 5 | po-usd-to-uat |
usd/ST-XXX.md |
uat/ST-XXX.md per story |
Execution Steps
Step 0 — Setup
- Confirm the feature name (use
$ARGUMENTSif provided, otherwise ask) - Create the feature folder structure:
features/{feature-name}/ ├── po/ │ ├── usd/ │ └── uat/ ├── design/ ├── pm/ └── code/ - If a brief already exists at
features/{feature-name}/brief.md, read it. Otherwise use the brief from$ARGUMENTSor ask the user.
Step 1 — PRD (po-brief-to-prd)
- Read the brief
- Activate
po-brief-to-prdskill - Generate
features/{feature-name}/po/prd.md - Pause and show the PRD to the user
- Ask: "PRD looks good? Proceed to User Story Map, or revise first?"
Step 2 — USM (po-prd-to-usm)
- Read
prd.md - Activate
po-prd-to-usmskill - Generate
features/{feature-name}/po/usm.md - Show the user story map to the user
- Proceed automatically to Step 3 (unless user says stop)
Step 3 — USL (po-usm-to-usl)
- Read
usm.md - Activate
po-usm-to-uslskill - Generate
features/{feature-name}/po/usl.mdwith MoSCoW prioritization - Show the story list (count of Must/Should/Could/Won't)
- Ask: "Proceed to write acceptance criteria for all Must-Have stories?"
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.
- 12d ago First seen · 126 lines · 0 tokens per session scan A 262019d43c50
po-pipeline is a command published in the GitHub repository karlng279/ai-ready-product-workflow-v2 (6 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,151 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.