update-docs

update-docs is a skill for Claude Code from nirecom/agents. It costs 12 tokens per session (1,697 once invoked), scanned A, original, MIT.

A workflow for updating project documentation after code or configuration changes. It covers Markdown files, including a project README and changelog.

In plain words
What is it for?
Reviewing recent Git changes and updating README, changelog, and documentation files.
Why use it?
It helps keep instructions and public documentation aligned with the current codebase.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Good fit Reviewing recent Git changes and updating README, changelog, and documentation files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nirecom/agents/update-docs
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.

Any agent
npx skills add nirecom/agents --skill update-docs
Clone the repo
git clone --depth 1 https://github.com/nirecom/agents

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 update-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirecom/agents/update-docs/github.svg)](https://agentmods.dev/skills/nirecom/agents/update-docs)
Your own site
<a href="https://agentmods.dev/skills/nirecom/agents/update-docs"><img src="https://agentmods.dev/badge/skills/nirecom/agents/update-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/nirecom/agents/update-docs"><img src="https://agentmods.dev/badge/skills/nirecom/agents/update-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,697 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 $0.00012 $0.01697
Opus 5.5 $0.00005 $0.00679
Sonnet 5.5 $0.00002 $0.00339
Haiku 4.5 $0.00001 $0.00170

Measured today against content hash 899247ebb235, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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.

skills/update-docs/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update all project documentation to reflect recent changes.

Docs directory: docs/ within the current project root. Target files: all .md files in docs/ that already exist, plus README.md in the project root.

Procedure

UD-0. Read rules/docs.md. It is on-demand-only and never auto-injected, so this Read is mandatory. Read rules/coding.md here too — same on-demand-only status; its Public GitHub Rules govern every doc written in UD-4 and after. UD-1. Gather recent changes:

  • Run git diff and git diff --cached to capture uncommitted and staged changes (current session's work, not yet in git log)
  • Run git log --oneline -20 for committed history UD-2. Read current docs: Read all target docs files.
  • README.md (repo root) is required for all repos. Create it first if missing — highest priority.
    • Goal: make the reader think "I want to use this" — crisp features, "what it does for you"
    • Initial install/setup instructions go here, not in ops.md
  • CHANGELOG.md (repo root) for public repos. Create if missing (no manual seed needed — first run starts from here).
  • When docs/glossary-user*.md or docs/glossary-internal*.md exists, Read rules/docs/glossary.md (on-demand-only) so its entry criteria drive the UD-3 glossary check. UD-3. Identify gaps: Compare git log against each document's content. Look for:
  • Unrecorded commits or phases
  • Architecture/design changes not yet documented
  • New incidents or bug fixes
  • Infrastructure or operational changes
  • Progress updates
  • README.md: Update when a user-visible feature is added or changed, install/usage steps shift, or an existing bullet no longer accurately reflects real behavior.
  • Glossary promotion: list the user / internal rows of <INTENT_MD> ## Glossary (<INTENT_MD> = the output of node "$AGENTS_MAIN_ROOT/bin/plan-artifact-path" --stage intent) as promotion candidates in the UD-4 proposal; do not write yet.
  • Glossary entries: never add one outside glossary promotion. UD-4. Propose updates: For each file that needs updating, present:
  • Before drafting History/Changelog bullets: apply the language configured by DOCS_LANG_PUBLIC / DOCS_LANG_PRIVATE, routed by repo visibility — one policy covers both history and changelog
  • Which sections need changes and why
  • Specific additions or modifications UD-5. CONFIRM_DOCS gate: Gate check: apply skills/_shared/confirm-plan.md CPA-3 — run next-step --gate and follow GATE_ACTION.
  • GATE_ACTION=ask: present the UD-4 proposal via AskUserQuestion and wait for approval before applying edits.
  • GATE_ACTION=proceed: apply the edits and continue to UD-6 without waiting.
  • When applying, run node "$AGENTS_MAIN_ROOT/bin/glossary-promote" "<INTENT_MD>" "<project-root>" first, then replace each promoted entry's Related: TODO with a link to the doc that owns the term. UD-6. Propagate to parent docs: If the project has a parent-level summary doc (e.g. an engineering hub), update it too. Skip for repo-local docs/.
  • Skip infrastructure.md — delegate to /update-infrastructure instead. UD-7. Commit separately: If docs are in a separate repo, commit each repo independently

Read the full file on GitHub · 85 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. today Changed 899247ebb235
  2. 4d ago Changed · +3 lines 500089169c13
  3. 7d ago Changed 24dd0829c7c8
  4. 17d ago Changed 4d56b21205e3
  5. 21d ago Changed 1cae6bf37902
  6. 29d ago Changed · +2 lines e54d2c12faae
  7. 1mo ago Changed · +2 lines 378836305429
  8. 1mo ago First seen · 78 lines · 12 tokens per session scan A 2aaed8ffe688

Subscribe to this mod's changes

update-docs is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,697 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens