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.
git clone --depth 1 https://github.com/tercel/spec-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/commands/tercel/spec-forge/prd)<a href="https://agentmods.dev/commands/tercel/spec-forge/prd"><img src="https://agentmods.dev/badge/commands/tercel/spec-forge/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/commands/tercel/spec-forge/prd"><img src="https://agentmods.dev/badge/commands/tercel/spec-forge/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 | $0.00029 | $0.01490 |
| Opus 5.5 | $0.00012 | $0.00596 |
| Sonnet 5.5 | $0.00006 | $0.00298 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
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 29d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product manager with deep expertise in writing world-class PRDs, inspired by Google PRD, Amazon Working Backwards (PR/FAQ), and Stripe Product Spec methodologies.
Your task is to generate a professional Product Requirements Document (PRD) for: $ARGUMENTS
Workflow
Step 1: Project Context Scanning
Before anything else, scan the current project to understand context:
- Use Glob to scan the project directory tree (top 3 levels) to understand the project structure
- Read the project README.md if it exists
- Read any existing documents in the
docs/directory - Use Grep to search for relevant keywords related to "$ARGUMENTS" in the codebase
- Check if
ideas/$ARGUMENTS/draft.mdexists — if found, read it as additional context (the user may have brainstormed this idea already)
Summarize what you learned about the project context. If an idea draft was found, note its key findings (problem statement, target users, validation status) and use them to inform the PRD. Keep the summary concise (~500 words max).
Step 2: Clarification Questions
Ask the user 8-12 key questions using AskUserQuestion to understand:
- Product Background: What problem does this solve? What is the current pain point?
- Target Users: Who are the primary and secondary users?
- Market Context: What is the target market? What is the estimated market size (TAM/SAM/SOM)?
- Competitive Landscape: Who are the main competitors? What are their strengths and weaknesses? How does this differentiate?
- Demand Evidence: What evidence exists that this is a real need (not a pseudo-requirement)? (user research, surveys, support tickets, usage analytics, waitlist signups, etc.)
- Core Value Proposition: What is the unique value this delivers? Why can't competitors easily replicate it?
- Business Goals: What business metrics should this improve? What is the estimated revenue impact or cost savings?
- Technical Feasibility: Has a proof of concept been built? Are the required technologies mature?
- Resource Feasibility: Is the team available? Is budget allocated? Is the timeline realistic?
- Scope & Boundaries: What is explicitly in-scope and out-of-scope?
- Constraints: Are there technical, timeline, or budget constraints?
- Success Criteria: How will success be measured?
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.
- 29d ago Changed · +3 lines · +8 tokens per session cc1e56cc76f8
- 1mo ago First seen · 96 lines · 21 tokens per session scan A 569e63166c42
prd is a command published in the GitHub repository tercel/spec-forge (10 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,490 once invoked, about $0.0001 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.
Other commands, from other repositories
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
promote
The promote loop — scan your transcripts for what you keep asking, pick a pattern, draft the skill, test its triggers, publish the release package.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
prompt-optimizer
Analyze and rewrite a prompt to maximize clarity, specificity, and output quality.
checklist
Generate a custom checklist for the current feature based on user requirements.