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 siarhei-belavus/agent-public --skill write-a-prdgit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/write-a-prd)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/write-a-prd"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/write-a-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/skills/siarhei-belavus/agent-public/write-a-prd"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/write-a-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 | $0.00035 | $0.00717 |
| Opus 5 | $0.00017 | $0.00358 |
| Sonnet 5 | $0.00007 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
write-a-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 9d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user define a product requirement clearly enough that it can be planned and implemented safely.
Your job is to interview the user, inspect the relevant codebase where useful, resolve major ambiguities, and then write a concrete PRD file.
Process
- Clarify the request
Ask focused questions until you understand:
- the user problem
- target users or actors
- desired outcomes
- major constraints
- known edge cases
- what is explicitly out of scope
Keep questions high-signal. Avoid long questionnaires when a few targeted questions will do.
- Explore the codebase
Inspect the existing code to understand:
- related modules and boundaries
- existing terminology
- integration constraints
- implementation hotspots likely to shape scope
Do not over-index on current implementation details. The PRD should describe the desired product behavior and key system constraints, not prescribe fragile code-level mechanics.
- Resolve ambiguity
Before writing, make sure the following are reasonably clear:
- problem statement
- user value
- success criteria
- important workflows
- boundaries and exclusions
- risks, dependencies, or unknowns worth calling out
If critical ambiguity remains, call it out explicitly in the PRD instead of pretending it is resolved.
- Create the PRD folder
Create a dedicated folder for the PRD:
.prd/<prd-slug>/
Inside it, write the PRD file at:
.prd/<prd-slug>/prd.md
Also reserve these sibling folders for downstream artifacts when relevant:
.prd/<prd-slug>/issues/.prd/<prd-slug>/plans/.prd/<prd-slug>/rfcs/
Use a short kebab-case slug derived from the feature or initiative name.
- Write the PRD
Use this structure:
# <Feature / Initiative Name>
## Summary
A short description of the feature and why it matters.
## Problem
What problem is being solved? Who has this problem?
## Goals
- Goal 1
- Goal 2
## Non-Goals
- Not in scope 1
- Not in scope 2
## Users / Actors
- Primary user or actor
- Supporting actor or system
## Requirements
### Functional
- Requirement 1
- Requirement 2
### Non-Functional
- Performance / reliability / operational constraints
- Security / compliance / UX constraints
## User Flows
- Flow 1
- Flow 2
## Success Criteria
- Metric or observable outcome 1
- Metric or observable outcome 2
## Risks / Constraints / Dependencies
- Risk or dependency 1
- Risk or dependency 2
## Open Questions
- Question 1
- Question 2
Keep the document specific and actionable. Prefer concrete outcomes, constraints, and flows over vague aspirations.
- Final response
In your final response:
- give a short summary of what was clarified
- provide the final PRD path:
.prd/<prd-slug>/prd.md - mention any major open questions still unresolved
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.
- 9d ago First seen · 123 lines · 35 tokens per session scan A 059ac3f91bf6
write-a-prd is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 717 once invoked, about $0.0002 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.