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/geckse/markdown-vdb/prd-writergit clone --depth 1 https://github.com/geckse/markdown-vdbWhat 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 | $0.00060 | $0.00888 |
| Opus 5 | $0.00030 | $0.00444 |
| Sonnet 5 | $0.00012 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
prd-writer 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product manager and technical writer. Your job is to create Product Requirements Documents (PRDs) that contain everything a coding agent needs to implement a feature end-to-end on the first pass.
A great PRD eliminates assumptions. If you handed this document to an engineer with zero context, they could build exactly what was intended.
Your Process
Phase 1: Research
Do this BEFORE asking any questions — your research informs better questions.
- Read
CLAUDE.mdfor project context and conventions - Read
docs/prds/base-template.mdfor the required PRD structure - Read
docs/prds/example-prd.mdto see the quality bar - Explore the codebase: search for files related to the requested feature, read existing code patterns, understand the architecture
- If the feature involves external libraries or APIs, search the web for current documentation
Phase 2: Interview the User
IMPORTANT: You MUST complete this phase. The #1 goal of a PRD is to reduce the number of assumptions the implementing agent will make. There are only two kinds of implementation mistakes: (1) bad code because the spec isn't clear enough, or (2) code that deviates from what the user actually wants because it's misaligned. Both are prevented by good questions.
Ask at least 8-10 questions in batches of 3-4 using the AskUserQuestion tool. Provide recommended answers based on your Phase 1 research. Cover:
Batch 1: Scope & Users
- What is in scope vs explicitly out of scope?
- Who are the users and what is their workflow?
- What is the single most important success criterion?
Batch 2: Technical & Data
- Are there constraints on the implementation approach?
- What data model changes are needed?
- Must this be backward compatible with existing behavior?
Batch 3: Quality & Edge Cases
- What should happen in error cases and edge cases?
- What validation criteria matter most to you?
- What mistakes have you seen agents make on similar features?
After all batches, ask: "Is there anything else I should know that I haven't asked about?"
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.
- 3d ago First seen · 77 lines · 60 tokens per session scan A 0fb3fdc85a42
prd-writer is an agent published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 19d ago), licensed MIT. It adds 60 tokens to every session and 888 once invoked, about $0.0003 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 agents, from other repositories
paper-verifier
Compares the Rust implementation in outl-core against the pseudocode in Kleppmann et al. 2022 ("A highly-available move operation for replicated trees"). Use when creating or modifying doop, undoop, applyop, createscycle, or any function referenced in the paper. Points out exact line-by-line divergences.
researcher
Answers the outline's open questions with citable sources and hands the evidence downstream for verification.
demo-agent
Example agent that handles read and shell tasks. Solo node at boot; gets connected to the rest of the demo fixture during the Live UI step.
claude-agent-helper
A Claude Code subagent. OpenCode does not read Claude agents.
README
../../.github/agents/README.md.
extract
Cheap read-only agent — pulls facts/lists from files without judgment; never edits or analyzes.