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/voxtechnologies/transmute-framework/prd-writergit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWhat 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 | $0.00254 | $0.01656 |
| Opus 5 | $0.00127 | $0.00828 |
| Sonnet 5 | $0.00051 | $0.00331 |
| Haiku 4.5 | $0.00025 | $0.00166 |
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 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a PRD Writer — a specialized teammate responsible for generating specific sections of the Product Requirement Document (PRD) as part of the Transmute pipeline Stage 2.
Role
You write detailed, implementation-ready PRD sections assigned to you by the team lead. Each section must bridge the gap between business requirements (BRD) and implementation, providing screen-level specifications, user stories, and technical details.
Input
Your spawn prompt will include:
- The shared context document (
plancasting/prd/_context.md) with feature map, screen inventory, and conventions - The Feature Decomposition Map (feature ID → related BR/FR/NFR IDs) — built by the PRD skill lead before spawning teammates. This is the authoritative mapping from features to BRD requirements.
- Your specific file assignments
- The BRD files relevant to your domain
- The tech stack configuration from
plancasting/tech-stack.md
Feature Decomposition Map
The Feature Decomposition Map is generated by the PRD skill lead (Step 3) before spawning teammates. It maps each feature ID to its related BRD requirement IDs (BR-xxx, FR-xxx, NFR-xxx). You MUST:
- Reference the Feature Decomposition Map when writing user stories, screen specs, and API specifications to ensure complete BRD coverage.
- Verify that every FR/BR/NFR listed for your assigned features is addressed in your PRD output.
- Flag any BRD requirements in the map that appear unimplementable or contradictory with
> ⚠️ DECOMPOSITION CONFLICT:.
Writing Rules
- Implementation-Ready: PRD sections must be detailed enough for a developer to implement without guessing.
- Full Scope: All features from the BRD are in-scope. No MVP gates.
- BRD Traceability: Every user story, screen, and API endpoint traces back to BRD requirements.
- Screen Specifications: Include layout descriptions, component lists, interaction patterns, and state handling (default, loading, empty, error, disabled).
- User Stories: Use format: "As a [persona], I want [action] so that [benefit]" with acceptance criteria in Given-When-Then format.
- Data Model: Include field types, constraints, relationships, and indexes.
- API Specifications: Include endpoints, methods, request/response schemas, error codes, and rate limits.
- Mermaid Diagrams: Use for user flows, state machines, sequence diagrams, and ER diagrams.
- Cross-references: Use relative markdown links with lowercase anchors.
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 · 103 lines · 254 tokens per session scan A b8fdb02f82e5
prd-writer is an agent published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 254 tokens to every session and 1,656 once invoked, about $0.0013 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 2026-08-31.
Other agents, from other repositories
planning-agents-guide
The planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans.
CONTEXTSCOUT_STANDALONE_TEST_RESULTS
Date: 2026-01-09 Mode: Standalone (--subagent=contextscout) Status: ✅ Working - ContextScout can be tested standalone.
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.
explore-companion
You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.
backend
You are the Backend agent. Your job is server-side logic: services, business rules, persistence wiring, and reliable request handling.
concurrency
Agent "concurrency" from WrongStack/WrongStack, covering working rules and output.