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.
git clone --depth 1 https://github.com/pmprompt/claude-plugin-product-managementWrote 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/pmprompt/claude-plugin-product-management/write-prd)<a href="https://agentmods.dev/commands/pmprompt/claude-plugin-product-management/write-prd"><img src="https://agentmods.dev/badge/commands/pmprompt/claude-plugin-product-management/write-prd/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/pmprompt/claude-plugin-product-management/write-prd"><img src="https://agentmods.dev/badge/commands/pmprompt/claude-plugin-product-management/write-prd.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 | $0.00012 | $0.00301 |
| Opus 5.5 | $0.00005 | $0.00120 |
| Sonnet 5.5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
write-prd 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 2d 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.
What it actually says
/write-prd — PRD Creation Workflow
Comprehensive product requirements document from feature idea to implementation plan.
What It Does
Creates a structured PRD with problem statement, solution design, success metrics, requirements, and implementation details.
When to Use
- Starting a new feature or product initiative
- Need to align engineering, design, and stakeholders
- Before beginning development work
- Documenting validated discovery findings
Workflow
-
Problem & Solution — Articulate the problem, proposed solution, and success metrics (uses
prd-writerskill) -
User Stories & Acceptance Criteria — Break down into implementable stories (uses
prd-writerskill) -
Requirements & Risks — Define functional/technical requirements and mitigation plans (uses
prd-writerskill)
Usage
/write-prd [feature name or description]
Example:
/write-prd Smart notification system that reduces alert fatigue
Output
- Complete PRD (8 sections)
- User stories with acceptance criteria
- Success metrics and measurement plan
- Implementation timeline and dependencies
Next Steps After /write-prd
- Share with Product Trio for feedback
/plan-launch— Create go-to-market plan- Hand off to engineering for estimation
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.
- 2d ago Changed · +5 lines · +12 tokens per session ab02c894aea0
- 1mo ago First seen · 47 lines · 0 tokens per session scan A c7ad38a80e9d
write-prd is a command published in the GitHub repository pmprompt/claude-plugin-product-management (53 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 301 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
workflow-design-sprint
Run the Design Sprint workflow (5-day prototype-and-test arc producing a Decider's build/iterate/pivot/stop call).
workflow-foundation-sprint
Run the Foundation Sprint workflow (2-day strategic-alignment arc producing a Founding Hypothesis).
chain
Run an ad-hoc ordered chain of pm-skills with shared context (ephemeral; routes to the pm-workflow-orchestrator).
workflow-foundation-to-design
Run the end-to-end Foundation Sprint + Design Sprint workflow with narrative handoff.
workflow-feature-kickoff
Run the Feature Kickoff workflow (problem -> hypothesis -> PRD -> stories).
workflow-post-launch-learning
Run the Post-Launch Learning workflow (instrumentation -> dashboard -> results -> retro -> lessons).