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 agentmods add commands/assafkip/prd-os/prd-startgit clone --depth 1 https://github.com/assafkip/prd-osWrote 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/assafkip/prd-os/prd-start)<a href="https://agentmods.dev/commands/assafkip/prd-os/prd-start"><img src="https://agentmods.dev/badge/commands/assafkip/prd-os/prd-start.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00284 |
| Opus 5 | $0.00009 | $0.00142 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
prd-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
88% identical to prd-start — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Create a new PRD from the template. The slug becomes part of the PRD id
(prd-<slug>-YYYY-MM-DD). Slug must be kebab-case.
The runner enforces two invariants:
- No other PRD is active and non-archived.
- No issue is active (cross-runner concurrency guard).
Run:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_runner.py" new "$1" --owner "${2:-${USER:-unknown}}"
If the command exits non-zero, surface stderr verbatim. Do not retry. Common rejections:
- slug format (not kebab-case)
- active PRD (advise
/prd-archiveor clear) - active issue (advise closing the issue first)
After success, read the new PRD spec file to the author and ask them to fill in:
- Problem (concrete, observed, measurable)
- Goals and non-goals
- Proposed approach
- Risks and rollback
- Open questions
Do not auto-draft PRD content. The PRD is the author's contract. Auto-drafting creates sycophantic PRDs that pass review because Claude agreed with itself.
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.
- 4d ago First seen · 33 lines · 17 tokens per session scan A c9b57e5675e0
prd-start is a command published in the GitHub repository assafkip/prd-os (10 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 284 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to prd-start, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
adopt
Adopts RENATA in an existing codebase — reverse-engineers the technical pattern, feature inventory, as-built specs and a retroactive PRD, confirming every item with you.
plan-phase
Wraps superpowers:writing-plans with RENATA guardrails to produce a method-compliant, ADR-respecting execution plan reviewed by the architect.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
adr
Formalizes an ADR from a technical decision using the Nygard format and syncs its enforcement block in rules.yaml.
assumption-test
Surfaces the riskiest business assumption behind the PRD and designs the cheapest test to falsify it before building.
bug-report
Converts a raw bug report from production into a structured, severity-classified item and routes it to the right next step.