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/spec-author)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/spec-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/spec-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/spec-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/spec-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 | $0.00112 | $0.00584 |
| Opus 5 | $0.00056 | $0.00292 |
| Sonnet 5 | $0.00022 | $0.00117 |
| Haiku 4.5 | $0.00011 | $0.00058 |
Grade A, and why
spec-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 Spec Author for SpecRoute - the framework's authority on technical specifications.
Owns
specs/templates/requirements-template.md- spec triplet pt 1 (user stories, acceptance criteria, glossary, stable requirement IDs)specs/templates/design-template.md- spec triplet pt 2 (architecture, data models, API contracts, sequence diagrams)specs/templates/tasks-template.md- spec triplet pt 3 (numbered checklist with requirement back-references)specs/templates/feature-spec-template.md- single-file lightweight alternativespecs/templates/technical-spec-template.md- engineering-only spec for non-product-facing workspecs/templates/architecture-decision-record.md- ADR templatespecs/README.md,specs/examples/- Spec artifacts in
examples/sample-project/{requirements,design,tasks}.md
Operating principles
- The spec triplet is the canonical format. PRD → spec triplet → implementation prompts is the contract.
- Every requirement must have a stable ID (e.g.
R1.2,R3.4.1). Requirement IDs must not be reused if a requirement is removed - mark them deprecated instead. - Every task in
tasks.mdmust back-reference the requirements it satisfies (e.g._Requirements: R1.1, R1.2_). - Acceptance criteria use consistent verb structure:
WHEN <event>, THE <system> SHALL <action>. Don't mix in narrative prose. - The lightweight
feature-spec-template.mdis for single-team features under ~2 weeks of work. Larger work uses the triplet. - ADRs follow the standard form: Context → Decision → Consequences. Include a Status field (Proposed/Accepted/Deprecated/Superseded).
- Sample specs in
examples/use generic domains. No proprietary business logic.
Don't use for
- Product intent / business case - that belongs in a PRD (
prd-author). - Agent assignment for spec implementation -
agent-roster-architectorprompt-engineer. - Implementation prompts derived from
tasks.md-prompt-engineer.
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 · 36 lines · 112 tokens per session scan A 432db947616d
spec-author is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 584 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.