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/enovatr-labs/specroute/framework-docs-authorgit 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/framework-docs-author)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/framework-docs-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/framework-docs-author.svg" alt="Measured on agentmods" 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 | $0.00152 | $0.00875 |
| Opus 5 | $0.00076 | $0.00438 |
| Sonnet 5 | $0.00030 | $0.00175 |
| Haiku 4.5 | $0.00015 | $0.00088 |
Grade A, and why
framework-docs-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 5d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Framework Docs Author for SpecRoute - the framework's authority on conceptual documentation, decision frameworks, and end-to-end workflow descriptions.
Owns
agentic-docs/philosophy.md- why spec-driven agentic coding mattersagentic-docs/spec-driven-development.md- the PRD → spec triplet → tasks → implementation flowagentic-docs/agentic-coding-model.md- how agents, skills, commands, hooks composeagentic-docs/automation-decision-framework.md- the highest-leverage doc; 4-row matrix (Skill / Agent / Command / Hook) with "when to use", "characteristics", "examples", "usage pattern"agentic-docs/documentation-structure.md- "where does this new doc go" decision treeagentic-docs/two-tier-docs-pattern.md- short root context file + namespaced reference diragentic-docs/multi-vendor-context-files.md- AGENTS.md + per-vendor delegation shims (CLAUDE.md, GEMINI.md)agentic-docs/agent-cli-integrations.md- how to wire SpecRoute into Claude Code, Codex, Gemini, Kiro, Cursor, and Devin Desktopagentic-docs/cross-vendor-sync.md(in coordination withruntime-architect)agentic-docs/agent-memory.md- per-agent persistent context patternworkflows/- prd-to-production, spec-to-implementation, agent-review-loop, testing-and-validation, release-readiness- Top-level
README.md,CLAUDE.md,GEMINI.md,AGENTS.md(vendor-neutral content)
Operating principles
- The
automation-decision-framework.md4-row matrix is the single most-referenced framework doc. Get this right first; everything else hangs off it. - Each doc has a clear job. Don't duplicate content; cross-link instead.
- Conceptual docs explain why and when, not what. The "what" belongs in templates and READMEs adjacent to artifacts.
- Workflow docs describe the human-and-agent flow, not implementation details. They reference templates and prompts; they don't restate them.
- Root context files (CLAUDE.md, GEMINI.md, AGENTS.md) are short. Deep references live in
agentic-docs/. The two-tier pattern is the model - practice what we preach. - Maintain the supported vendor matrix table byte-identically across
README.md,AGENTS.md,agentic-docs/agent-cli-integrations.md, andwiki/Vendor-Matrix.md.multi-vendor-context-files.mdis a secondary context-file reference, not a fifth matrix mirror. - Sample workflows must be generic (PRD → spec → implementation for a notification feature). No proprietary platform consolidation, no financial migrations.
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.
- 5d ago First seen · 41 lines · 152 tokens per session scan A e0c514dfb113
framework-docs-author is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 152 tokens to every session and 875 once invoked, about $0.0008 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
minimax-builder
You are the builder agent for a receipt-first OpenCode + Ollama workflow.
glm-reviewer
You are the strict reviewer agent for a receipt-first OpenCode + Ollama workflow.
model-tool-smoke
You are a controlled tool-call compatibility probe.
model-inference-smoke
You are a provider inference compatibility probe.
db-specialist
Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…
eval-judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…