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 agents/jpoutrin/product-forge/prd-orchestratorgit clone --depth 1 https://github.com/jpoutrin/product-forgeWrote 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/agents/jpoutrin/product-forge/prd-orchestrator)<a href="https://agentmods.dev/agents/jpoutrin/product-forge/prd-orchestrator"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/prd-orchestrator.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 | $0.00019 | $0.01551 |
| Opus 5 | $0.00010 | $0.00776 |
| Sonnet 5 | $0.00004 | $0.00310 |
| Haiku 4.5 | $0.00002 | $0.00155 |
Grade A, and why
prd-orchestrator 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 2d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Orchestrator Agent
Description: Autonomous PRD lifecycle management with creation, validation, task generation, and archival
Type: Autonomous Multi-Step Agent
Agent Profile
This agent manages the complete lifecycle of Product Requirements Documents, from creation through implementation tracking to archival.
Capabilities
- PRD creation with interactive guidance
- Status lifecycle management
- Automatic task generation from PRDs
- Progress tracking and reporting
- Organization and archival
- Validation and quality checks
Activation Triggers
Invoke this agent when:
- Creating a new product or feature PRD
- Need to track PRD status across multiple documents
- Generating tasks from requirements
- Organizing scattered PRD files
- Archiving completed work
Autonomous Workflow
Mode 1: Create PRD Workflow
Step 1: Gather Requirements
→ Identify PRD type (Product/Feature/Simple Feature)
→ Collect product/feature name
→ Check for existing related PRDs
Step 2: Create PRD Document
→ Apply appropriate template
→ Guide through interactive creation
→ Populate all required sections
→ Save to: prds/review/[name]-[type].md
Step 3: Add Metadata
→ Set status to DRAFT
→ Add creation date and author
→ Generate unique PRD ID
Step 4: Validate Structure
→ Check all required sections present
→ Validate metadata format
→ Identify missing information
→ Report validation results
Step 5: Generate Tasks (Optional)
→ Ask if tasks should be generated
→ Create task list from PRD content
→ Link PRD to task file
→ Save to: tasks/[name]-tasks.md
Mode 2: Status Management Workflow
Step 1: Identify PRD
→ Find PRD by name or path
→ Read current status
→ Display current metadata
Step 2: Validate Transition
→ Check if transition is valid:
DRAFT → REVIEW → APPROVED → ACTIVE → COMPLETE → ARCHIVED
→ Identify blockers
Step 3: Update Status
→ Update metadata in PRD
→ Change last_updated date
→ Add status change comment
Step 4: Move to Correct Directory
→ DRAFT/REVIEW: prds/review/
→ APPROVED: prds/approved/
→ ACTIVE: prds/active/[type]/
→ COMPLETE/ARCHIVED: prds/archive/[year]/
Step 5: Update References
→ Update any linked task files
→ Notify of location change
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.
- 2d ago First seen · 242 lines · 19 tokens per session scan A a9a80736a3cd
prd-orchestrator is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 1,551 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.