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/yassinello/claude-plugin-prd-workflow/setup-prdgit clone --depth 1 https://github.com/Yassinello/claude-plugin-prd-workflowWrote 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/yassinello/claude-plugin-prd-workflow/setup-prd)<a href="https://agentmods.dev/commands/yassinello/claude-plugin-prd-workflow/setup-prd"><img src="https://agentmods.dev/badge/commands/yassinello/claude-plugin-prd-workflow/setup-prd.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 | $0.02530 |
| Opus 5 | $0.00009 | $0.01265 |
| Sonnet 5 | $0.00003 | $0.00506 |
| Haiku 4.5 | $0.00002 | $0.00253 |
Grade A, and why
setup-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 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.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup PRD Command
Prepare development environment for a PRD by creating a feature branch, auto-assigning, and moving to Ready.
Purpose
Create isolated development environment for PRD:
- Create feature branch
- Set up Git worktree in
worktrees/(MANDATORY) - Auto-assign to current user
- Move PRD to Ready (02-ready/)
- Update WORK_PLAN.md
- Keep main branch active in current window (CRITICAL)
- Accept draft PRDs (with warning) for parallel workflow
⚠️ Critical Rules (MANDATORY)
1. Worktree Location
ALWAYS use worktrees/ subdirectory for consistency:
# ✅ CORRECT (Standard as of 2025-11-02)
git worktree add worktrees/prd-007-oauth2-integration feat/PRD-007-oauth2-integration
# ❌ WRONG (Old pattern - deprecated)
git worktree add ../watchora-prd-007 feat/PRD-007-oauth2-integration
Rationale:
- ✅ Centralized organization (all worktrees in one place)
- ✅ Easier to find and manage
- ✅ Cleaner project structure
- ✅ Consistent with modern Git worktree best practices
2. Branch Context
ALWAYS return to main branch after setup:
# After creating worktree, ensure we're on main
git checkout main
Rationale:
- ✅ Main window stays on
main(free for other work) - ✅ Feature work happens in separate Cursor window (worktree)
- ✅ No accidental commits to feature branch in main window
- ✅ Parallel workflow enabled
Step-by-Step Process
Step 1: List Available PRDs
Scan PRD directories for available PRDs:
# Check these directories:
- product/prds/01-draft/
- product/prds/02-ready/
- product/prds/03-in-progress/ (to show what's already being worked on)
Display table:
📋 **PRDs Available**
**Draft** (Review later on feature branch):
| # | PRD ID | Feature | Created |
|---|--------|---------|---------|
| 1 | PRD-007 | OAuth2 Integration | 2025-10-26 |
| 2 | PRD-008 | Dark Mode Support | 2025-10-26 |
**Approved** (Ready to code):
| # | PRD ID | Feature | Grade |
|---|--------|---------|-------|
| 3 | PRD-003 | Design System | A- |
| 4 | PRD-004 | Landing Page | B+ |
**In Progress** (Already being developed):
| # | PRD ID | Feature | Branch |
|---|--------|---------|--------|
| 5 | PRD-005 | API v2 | feature/PRD-005-api-v2 |
Which PRD? (number, PRD-XXX, or filename)
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 · 377 lines · 17 tokens per session scan A 6b9cb1bd9e67
setup-prd is a command published in the GitHub repository Yassinello/claude-plugin-prd-workflow (12 stars, last pushed 9mo ago), licensed MIT. It adds 17 tokens to every session and 2,530 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
sprint
Scope-boxed sprints over the backlog: one active sprint, explicit carry-over, a close that refuses to hide unfinished work.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
forge
Ore in, steel out. Full pipeline: plan → execute → verify. Use: /forge 'task', /forge --full, --discuss, --plan-only, --execute, --park, --resume.
lifecycle
Complete milestone lifecycle: audit, archive, and next version.
status
Show project progress, current phase, and next actions.