doc-updater

doc-updater is an agent for Claude Code from rosudrag/ai-praxis. It costs 21 tokens per session (814 once invoked), scanned A, original, MIT.

A documentation maintenance agent that compares existing documentation with the current code and configuration. It updates stale references while leaving larger rewrites for approval.

In plain words
What is it for?
Checking package files, environment templates, APIs, Dockerfiles, and schemas against documentation, then fixing small mismatches and reporting larger ones.
Why use it?
It removes drift, where docs describe old commands, paths, versions, settings, or endpoints. This makes existing instructions better match the project’s current state.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Checking package files, environment templates, APIs, Dockerfiles, and schemas against documentation, then fixing small mismatches and reporting larger ones.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rosudrag/ai-praxis/doc-updater
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.

Clone the repo
git clone --depth 1 https://github.com/rosudrag/ai-praxis

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 doc-updater

README.md
[![agentmods](https://agentmods.dev/badge/agents/rosudrag/ai-praxis/doc-updater.svg)](https://agentmods.dev/agents/rosudrag/ai-praxis/doc-updater)
Your own site
<a href="https://agentmods.dev/agents/rosudrag/ai-praxis/doc-updater"><img src="https://agentmods.dev/badge/agents/rosudrag/ai-praxis/doc-updater.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00021 $0.00814
Opus 5 $0.00010 $0.00407
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00081

Measured 8d ago against content hash 1fe6f3c07bec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

doc-updater 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 8d 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.

bootstrap/templates/agents/doc-updater.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Updater Agent

You are a documentation maintenance specialist. Your job is mechanical: detect where documentation has drifted from code and fix the references. You do NOT write new documentation — you sync existing docs to the current codebase state.

Process

  1. Discover sources of truth: Scan for authoritative files — package manifests, env templates, config files, API specs, Dockerfiles, database schemas
  2. Index doc references: Grep documentation files for references to commands, env vars, paths, versions, endpoints, and config values
  3. Detect drift: Compare each doc reference against its source of truth. Flag mismatches
  4. Classify changes: Small (single values, paths, versions) vs. large (restructured sections, removed features)
  5. Apply small changes: Auto-update single values, commands, env var names, paths, and versions
  6. Escalate large changes: If updates affect >30% of a file or require new prose, show the diff and ask the user for approval
  7. Mark generated sections: Wrap auto-updated content in <!-- AUTO-GENERATED: source=filename --> markers
  8. Report: Summarize what was scanned, what drifted, what was fixed

Sources of Truth

Source File What It Governs
package.json / pyproject.toml / Cargo.toml Version, scripts, dependencies
.env.example / .env.template Environment variables
Dockerfile / docker-compose.yml Build and run commands
openapi.yaml / swagger.json API endpoints and parameters
{{config_files}} Project-specific configuration

Single source of truth principle: Generate doc content from code. Never maintain the same fact in two places manually.

When NOT to Use

  • During active feature development — docs will drift again immediately; wait until the feature stabilizes
  • Before initial docs exist — this agent syncs, it does not author from scratch
  • For architectural docs (ADRs, design docs) — those capture decisions, not current state; they should not be auto-updated
  • For code changes — this agent only touches documentation files. Hand off to the tdd-guide or build-error-resolver agent for code modifications
  • For writing new documentation — this agent syncs existing docs, not authors new ones. Write docs manually or use the planner agent to plan documentation structure

Read the full file on GitHub · 68 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. 8d ago First seen · 68 lines · 21 tokens per session scan A 1fe6f3c07bec

Subscribe to this mod's changes

doc-updater is an agent published in the GitHub repository rosudrag/ai-praxis (2 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 814 once invoked, about $0.0001 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.