framework-docs-author

framework-docs-author is an agent for Claude Code from Enovatr-Labs/SpecRoute. It costs 152 tokens per session (875 once invoked), scanned A, original, Apache-2.0.

An authoring and review agent for documentation about a framework for building with coding agents. It covers development workflows, choosing between skills, agents, commands, and hooks, and connecting several vendor tools.

In plain words
What is it for?
Use it to write or revise framework guides, decision tables, documentation structure, multi-vendor context files, and agent-memory guidance.
Why use it?
It helps keep conceptual and workflow documentation organized, accurate, and understandable across different coding-agent environments.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

Install

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.

agentmods
npx agentmods add agents/enovatr-labs/specroute/framework-docs-author
Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

Made for: Claude Code.

Wrote 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.

agentmods badge for framework-docs-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/framework-docs-author.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/framework-docs-author)
Your own site
<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>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash e0c514dfb113, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/agents/framework-docs-author.md · 41 lines

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 matters
  • agentic-docs/spec-driven-development.md - the PRD → spec triplet → tasks → implementation flow
  • agentic-docs/agentic-coding-model.md - how agents, skills, commands, hooks compose
  • agentic-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 tree
  • agentic-docs/two-tier-docs-pattern.md - short root context file + namespaced reference dir
  • agentic-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 Desktop
  • agentic-docs/cross-vendor-sync.md (in coordination with runtime-architect)
  • agentic-docs/agent-memory.md - per-agent persistent context pattern
  • workflows/ - 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.md 4-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, and wiki/Vendor-Matrix.md. multi-vendor-context-files.md is 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.

Read the full file on GitHub · 41 lines

Changes

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.

  1. 5d ago First seen · 41 lines · 152 tokens per session scan A e0c514dfb113

Subscribe to this mod's changes

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.