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 closedloop-ai/claude-plugins --skill prd-creatorgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/prd-creator)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/prd-creator"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/prd-creator.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 5.1 | $0.00089 | $0.01797 |
| Opus 5 | $0.00044 | $0.00898 |
| Sonnet 5 | $0.00018 | $0.00359 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
prd-creator 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 yesterday.
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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Creator
Philosophy
We document for alignment, not approval. A PRD answers:
- What are we building and why?
- Who is it for?
- How do we know it worked?
- What's the smallest thing we can ship?
- Any compliance blockers?
Workflow Modes
Discovery Mode
When PM has a rough idea, guide them through conversationally:
- Problem — "What's the user pain or opportunity?"
- Evidence — "How do you know this matters?" (even anecdotal is fine)
- Why now? — "Why this over other things we could build? What's the cost of waiting?"
- Persona — "Who specifically has this problem?"
- Success — "If this works, what changes? How will we measure it?"
- First slice — "What's the smallest version that tests the hypothesis?"
- Risks — "Any compliance, security, or regulatory concerns? Any technical blockers?"
Don't ask all at once. Have a conversation. Fill gaps with reasonable assumptions and flag them as open questions.
See references/examples.md for a sample Discovery conversation.
Draft Mode
When ready to write, use assets/prd-template.md. The template includes:
- Overview — What the feature does and why it matters
- Background — Context, research, and strategic rationale
- Goals & Success Metrics — Measurable outcomes and targets
- User Stories — Stories with US-### IDs in As a / I want / So that format
- Requirements — Functional and non-functional requirements
- User Experience — Key workflows, edge cases, and error states
- Technical Considerations — Dependencies, constraints, architecture
- Acceptance Criteria — Testable conditions for completion
- Open Questions — Unresolved items with Q-### IDs
- Out of Scope — What's explicitly excluded
- Timeline & Milestones — Key dates and phases
- Risks & Mitigations — What could go wrong and how to address it
Story Expansion Mode
Use this mode to add acceptance criteria to stories before exporting to Jira. The PM workflow is:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 177 lines · 89 tokens per session scan A 4cfc21be34cf
prd-creator is a skill published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 89 tokens to every session and 1,797 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 2026-09-07.
Other skills, from other repositories
fleet
The single-pane session roster (/foundry:fleet) — every active Claude Code session joined to its foundry work-context (epic/atom/governance), over the NATIVE session list. Read-only/advisory. Trigger to see all your parallel sessions at a glance with their foundry context, or when supervising many sessions and asking…
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.