update

A command that checks which documentation needs changing after code is modified, using a code comparison, pull request, or file path.

In plain words
What is it for?
Use it after code changes to find affected documents and update them according to the project's writing rules.
Why use it?
It helps prevent documentation from becoming inaccurate when commands, settings, APIs, or other public parts of a project change.

Command

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 commands/edwardangert/docs-agent-plugin/update
Clone the repo
git clone --depth 1 https://github.com/EdwardAngert/docs-agent-plugin
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 1,288 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 $0.00021 $0.01288
Opus 5 $0.00010 $0.00644
Sonnet 5 $0.00004 $0.00258
Haiku 4.5 $0.00002 $0.00129

Measured yesterday against content hash b49afc1c5f43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update 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 yesterday.

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.

commands/update.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Docs for a Change

Keep documentation in sync with the code. Given a change, find the docs it affects and update them. This is the workflow that most benefits from running inside Claude Code, where the diff and the docs are both at hand.

The argument ($ARGUMENTS) can be a git ref or range (HEAD~3, main..feature), a PR number, or a path. If omitted, use the working-tree and staged changes against the base branch.

Process

1. Resolve the Config

Read .docs-assist/config.yml and .docs-assist/style.md if present, so updates match the project's conventions. See ${CLAUDE_PLUGIN_ROOT}/skills/docs-assist/reference/config-resolution.md.

2. Get the Change Set

Resolve $ARGUMENTS to a concrete diff:

  • A ref or range: git diff <range>.
  • A PR number: gh pr diff <number> (or check out the PR).
  • A path: git diff -- <path>, or read the file if it is uncommitted.
  • Nothing: git diff plus git diff --staged against the base branch.

3. Summarize What Changed

From the diff, extract the things docs describe:

  • New, renamed, or removed public APIs, endpoints, CLI commands, and flags.
  • Changed configuration keys, environment variables, and defaults.
  • Changed behavior, prerequisites, or required versions.
  • New features that need first-time documentation.

Write a short change summary. This is what drives the doc search and the updates.

4. Find Affected Docs

Locate the docs that reference what changed:

  • Start from llms.txt and frontmatter (keywords, related) to map the docs set.
  • Grep the docs directory for the changed symbols, flags, and key names.
  • Rank by how directly each doc depends on the change.

Separate confident matches (a doc documents a flag you renamed) from weak matches (a doc mentions a term in passing). Do not touch the weak matches without reason.

5. Update the Docs

Before editing, check the branch. If the working tree is on the default branch and the update will touch more than a file or two, offer to do the pass on a docs branch so the result arrives as a reviewable change set. Never commit to the default branch unless asked. The contributor's existing workflow (they may already be on a feature branch) wins.

Read the full file on GitHub · 79 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. yesterday First seen · 79 lines · 21 tokens per session scan A b49afc1c5f43

Subscribe to this mod's changes

update is a command published in the GitHub repository EdwardAngert/docs-agent-plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,288 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.