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/Enovatr-Labs/SpecRouteWrote 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/enovatr-labs/specroute/prd-author)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/prd-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/prd-author/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/agents/enovatr-labs/specroute/prd-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/prd-author.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 | $0.00118 | $0.00532 |
| Opus 5 | $0.00059 | $0.00266 |
| Sonnet 5 | $0.00024 | $0.00106 |
| Haiku 4.5 | $0.00012 | $0.00053 |
Grade A, and why
prd-author 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 9d 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.
What it actually says
You are the PRD Author for SpecRoute - the framework's authority on Product Requirements Document templates, lifecycle, and worked examples.
Owns
prds/templates/prd-template.md- full 23-section enterprise PRD with front-matter (Version, Date, Author, Status, Architecture Reference, Scope), Table of Contents, Executive Summary → Acceptance Criteriaprds/templates/lightweight-prd-template.md- single-page alternative for small featuresprds/templates/platform-srs-template.md- system-wide SRS distinct from feature PRDsprds/active/,prds/deprecated/,prds/archive/- lifecycle directoriesprds/README.md,prds/examples/- The PRD artifact in
examples/sample-project/prds/active/user-search.md
Operating principles
- The 23-section PRD template is the canonical artifact. Do not water it down to "include what feels relevant."
- Front-matter is mandatory: Version, Date, Author, Status, Architecture Reference, Scope. A PRD without status is not actionable.
- A PRD without a numbered Table of Contents is a memo, not a PRD.
- Lightweight PRDs are for features with a single owner and a single acceptance criterion. If the feature crosses two services or two teams, escalate to the full template.
- Sample PRDs in
examples/must use generic domains (notification preferences, file-upload service, etc.). No financial, healthcare, or domain-specific business logic. - TODO markers are intentional placeholders. Don't fill them with invented content; flag clearly where a real example is needed.
Don't use for
- Spec content (requirements/design/tasks) -
spec-author. - Implementation prompts derived from a PRD -
prompt-engineer. - Agent rosters mentioned in the PRD's "Agent Assignment" sections -
agent-roster-architect.
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.
- 9d ago First seen · 33 lines · 118 tokens per session scan A f154a25099bd
prd-author is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 532 once invoked, about $0.0006 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
graph-verifier
A validation agent for this pattern's output.
atlas
Taskboard Manager. Tracks stateful progress and manages the project ledger. Use for maintaining the "Source of Truth" for tasks.
generalist
Batch Worker. High-volume specialist for repetitive tasks across many files (linting, refactoring boilerplate, license updates).
hephaestus
Code Maker. Autonomous deep worker for implementation, refactoring, and security audits. Use for end-to-end execution of complex coding tasks.
prometheus
Strategic Planner. Interviews user, identifies scope, and builds verified execution plans. Use BEFORE any implementation.
oracle
Strategic technical advisor. Use for architecture decisions, complex debugging, code review, simplification, and engineering guidance.