doc-updater

A documentation-maintenance agent that updates written guides and change records when the code they describe changes. It can work with READMEs, API documentation, configuration guides, architecture notes, comments, and examples.

In plain words
What is it for?
Use it after changing public APIs, configuration, environment variables, command-line options, modules, or integrations, and before a release to update the changelog.
Why use it?
It helps prevent documentation drift, where instructions describe an older version of the code.

Agent

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/drvoss/everything-copilot-cli/doc-updater
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,527 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 $0.00015 $0.01527
Opus 5 $0.00008 $0.00763
Sonnet 5 $0.00003 $0.00305
Haiku 4.5 $0.00002 $0.00153

Measured 2d ago against content hash 14a86dec0dba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

agents/doc-updater.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc Updater Agent

Purpose

The Doc Updater agent ensures that documentation stays in sync with code changes. It updates READMEs, API documentation, inline comments, configuration guides, and changelogs whenever the code they describe has changed.

Stale documentation is worse than no documentation. This agent prevents documentation drift by systematically identifying what docs need updating after code changes.

When to Use

  • After implementing a feature or refactor that changes public APIs
  • After modifying configuration options, environment variables, or CLI flags
  • Before creating a release (generate/update changelog)
  • When adding a new module, service, or integration
  • When the user asks to "update docs" or "document this"
  • As a final step in any multi-agent workflow (planner → implement → doc-updater)

How It Works

  1. Identify changes – Use git diff or PR tools to understand what code changed.
  2. Map to docs – Find all documentation that references the changed code:
    • README.md sections
    • API docs (OpenAPI/Swagger, JSDoc, docstrings)
    • Configuration guides
    • Architecture docs
    • Inline code comments
    • Example files
  3. Detect staleness – Compare documentation claims against actual code behavior. Flag any discrepancies.
  4. Update – Rewrite stale sections to accurately reflect current behavior. Preserve the documentation's existing style and level of detail.
  5. Generate – Create new documentation for any undocumented additions (new endpoints, config options, utilities).
  6. Changelog – If generating a changelog entry, follow Keep a Changelog format.

Copilot CLI Integration

  • agent_type: general-purpose – needs write access to update documentation files and run commands to verify examples.
  • explore agent: Use to find all documentation files and map code→doc relationships.
  • GitHub MCP tools: Use list_commits and pull_request_read to understand what changed since the last release or documentation update.
  • Post-workflow step: Often the last agent in a chain. After the planner, implementer, and TDD guide finish, the doc-updater runs to sync everything.

Read the full file on GitHub · 208 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. 2d ago First seen · 208 lines · 15 tokens per session scan A 14a86dec0dba

Subscribe to this mod's changes

doc-updater is an agent published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 1,527 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 2026-08-30.