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 stark-ai-de/agent-skills --skill prd-writergit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/prd-writer)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/prd-writer"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/prd-writer/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/stark-ai-de/agent-skills/prd-writer"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/prd-writer.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 | $0.00056 | $0.00643 |
| Opus 5 | $0.00028 | $0.00321 |
| Sonnet 5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
prd-writer 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer
Goal
Create a clear product or implementation brief that preserves decisions, unresolved questions, scope, validation, and non-goals.
When to use
- The user asks for a PRD, implementation brief, product spec, or handoff spec.
- Current conversation context needs to become a durable planning artifact.
- Engineering, product, validation, and rollout expectations need one shared document.
When not to use
- The user only needs an ADR for a narrow repo-level decision.
- The task is ready for implementation and does not need a planning artifact.
- The user asks for a marketing document rather than product or engineering scope.
Inputs to inspect
- Current conversation, existing specs, issues, roadmap items, ADRs, and domain docs.
- User goals, constraints, target users, non-goals, and known decisions.
- Existing validation commands and release process when relevant.
Workflow
- Identify the audience and artifact type: PRD, implementation brief, or handoff spec.
- Separate problem, goals, non-goals, proposed solution, decisions, and open questions.
- Write user stories or use cases only when they clarify behavior.
- Include acceptance criteria and validation commands.
- Add rollout, migration, observability, docs, or support notes only when relevant.
- Keep unresolved questions explicit instead of pretending decisions are final.
- Ask before writing files unless the user requested a file update.
Safety rules
- Do not invent product decisions to make the brief look complete.
- Do not bury out-of-scope items in footnotes.
- Do not include private customer data, internal hostnames, or secrets.
- Do not turn implementation details into requirements unless the user decided them.
References
No bundled references. Use local domain docs and ADRs when present so terminology and decisions match the repository.
Scripts
No bundled scripts.
Output format
Return or write:
- Problem
- Goals
- Non-goals
- Users or stakeholders
- Proposed solution
- User stories or workflows
- Decisions
- Open questions
- Acceptance criteria
- Validation and rollout
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 · 88 lines · 56 tokens per session scan A 100e8f4d4da7
prd-writer is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 643 once invoked, about $0.0003 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
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-implement-story
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
openlore-write-tests
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.