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 jamesgray-ai/handsonai-plugins --skill writing-feature-prdsgit clone --depth 1 https://github.com/jamesgray-ai/handsonai-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/jamesgray-ai/handsonai-plugins/writing-feature-prds)<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/writing-feature-prds"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/writing-feature-prds/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/jamesgray-ai/handsonai-plugins/writing-feature-prds"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/writing-feature-prds.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 | $0.00043 | $0.07303 |
| Opus 5.5 | $0.00017 | $0.02921 |
| Sonnet 5.5 | $0.00009 | $0.01461 |
| Haiku 4.5 | $0.00004 | $0.00730 |
Grade A, and why
writing-feature-prds 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 1mo 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature PRD Workflow
Guide the user through creating a well-defined feature PRD (Product Requirements Document) before implementation.
Important: A PRD describes one feature — a single, buildable piece of work. If the user's idea is bigger than one feature (multiple epics, many capabilities), they should run /agentic-coding:writing-vision-briefs first to break it down. This skill takes one feature as input, not an entire vision.
When to Use This Skill
- User wants to build a new feature
- User mentions "create a spec", "create a PRD", "new feature", or "feature PRD"
- User wants to define requirements before coding
- User has completed a Vision Brief and is ready to spec out one of the features from the breakdown
Workflow Overview
| Phase | Goal |
|---|---|
| 1. Define | Create PRD in a specs/ directory |
| 2. Stress-test | Review for gaps and ambiguities |
| 3. Track | GitHub issue with type:feature label |
| 4. Handoff | Move to plan mode for implementation planning |
Phase 1: Define the Feature
First, figure out where the user is coming from:
Path A — Coming from a Vision Brief (recommended flow): If the user references a Vision Brief or a specific feature from a breakdown (e.g., "Write a PRD for email verification from specs/onboarding-vision.md"):
- Read the Vision Brief
- Find the specific feature in the Feature Breakdown section
- Systematically translate each Vision Brief section into PRD content using this mapping:
| Vision Brief Section | PRD Section | How to Translate |
|---|---|---|
| The Problem | Motivation | Scope the problem to this specific feature. Keep quantification from the brief. |
| Who Feels It | User Stories | Use as the user type(s) in story format. |
| Stakeholders | (note in issue) | Carry over to the GitHub issue body for review assignments. |
| Current State | Motivation | Add as context for why the current state is insufficient. |
| Alternatives Considered | Design Constraints | Note what was ruled out and why — these become constraints. |
| Strategic Context | Motivation | Include urgency signals that apply to this feature. |
| The Vision | Summary | Scope the vision statement down to this one feature. |
| Key Capabilities | User Stories + AC | Map relevant capabilities to stories with [MUST]/[SHOULD]/[COULD] criteria. |
| Inspiration | UI/UX Requirements | Pull in relevant design references for user-facing features. |
| What Success Looks Like | Success Metrics | Translate early signals and real outcomes into measurable metrics for this feature. |
| Risks & Assumptions | Open Questions + Assumptions | Risks you're unsure about → Open Questions. Things you're relying on being true but won't build/verify → the Assumptions section. |
| Dependencies | Dependencies & Prerequisites | Carry over dependencies relevant to this feature. |
| Constraints & Context | Design Constraints + NFRs | Split into design constraints and non-functional requirements. |
| Future Considerations | Future Considerations | Carry over items relevant to this feature's domain. |
What ships with it
1 file 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.
- 1mo ago Changed · -1 lines 57101fd37324
- 2mo ago First seen · 454 lines · 43 tokens per session scan A 1933a6fd9cd2
writing-feature-prds is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 7,303 once invoked, about $0.0002 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 2026-08-31.
writing-feature-prds compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-feature-prdsjamesgray-ai/handsonai-plugins | Skill | 8 | yesterday | MIT | A | 43 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |