update-docs

A documentation review workflow for updating Markdown files after changes on a Git branch. It compares the branch with a base branch and examines the changed source files to understand what the documentation should say.

In plain words
What is it for?
It helps inspect branch statistics and commit history, read changed source files, follow relevant dependencies, and update Markdown documentation to match the implementation. The default comparison branch is main unless another one is supplied.
Why use it?
It prevents documentation from falling out of date when code changes. The workflow uses the full context of changed files instead of relying only on a short diff summary.

Skill for Claude CodeCodex

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 skills/wolframresearch/agenttools/update-docs
Any agent
npx skills add WolframResearch/AgentTools --skill update-docs
Clone the repo
git clone --depth 1 https://github.com/WolframResearch/AgentTools

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 779 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 $0.00779
Opus 5 $0.00008 $0.00390
Sonnet 5 $0.00003 $0.00156
Haiku 4.5 $0.00002 $0.00078

Measured 2d ago against content hash 90e1330d6c8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-docs 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.

.claude/skills/update-docs/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Documentation for Branch Changes

Review all changes on the current branch compared to a base branch and update markdown documentation files to reflect those changes.

Base branch: Use $ARGUMENTS if provided, otherwise default to main.

Process

1. Understand the Changes

Start by identifying what changed on the current branch:

  • Run git diff <base>...HEAD --stat to see which files changed
  • Run git log <base>..HEAD --oneline to understand the commit history

Then fully read and explore every changed source file (not just tests or assets) until you completely understand the changes. The diff alone does not provide enough context — you must read the full files to understand how the changes fit into the surrounding code, what patterns are used, and what the code actually does.

For each changed source file:

  • Read the entire file (or at minimum the complete functions/sections that were modified)
  • Understand the purpose of the file and how the changes relate to its overall role
  • Follow references to other files if needed to understand dependencies or shared symbols
  • If a new file was added, read it completely

Build a thorough mental model of:

  • What new features, modules, or capabilities were added
  • What existing behavior changed
  • What new files, symbols, options, or configuration were introduced
  • What was removed or renamed
  • How the changes interact with the rest of the codebase

2. Inventory Documentation Files

Read ALL markdown documentation files that could be affected:

  • AGENTS.md (project structure, development patterns, file listings)
  • README.md (features, tools, options, API reference)
  • Every file in docs/ (tools, servers, clients, prompts, apps, testing, building, getting-started, etc.)

3. Identify What Needs Updating

For each documentation file, check whether the changes on the branch affect any of its content:

  • Project structure listings - Do they include new files/directories?
  • Feature lists - Do they mention new capabilities?
  • Tool tables - Do they list new tools or note changed tool behavior?
  • Option/config tables - Do they document new options or environment variables?
  • Server descriptions - Do they reflect changes to server configurations?
  • Related files sections - Do they reference new source files?
  • Cross-references/links - Are there broken links to renamed/removed sections?
  • Code examples - Are they still accurate?

Read the full file on GitHub · 82 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 · 82 lines · 15 tokens per session scan A 90e1330d6c8d

Subscribe to this mod's changes

update-docs is a skill published in the GitHub repository WolframResearch/AgentTools (82 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 779 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens