update-docs

update-docs is a skill for Claude Code from jessepinkman9900/claude-second-brain. It costs 62 tokens per session (896 once invoked), scanned A, original, MIT.

A documentation audit tool for claude-second-brain that compares recent changes with the project's docs and release log.

In plain words
What is it for?
Use /update-docs to review documentation gaps, getting-started instructions, and ship-log entries.
Why use it?
It finds shipped features or release entries that are missing from the documentation before asking for approval to edit them.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use /update-docs to review documentation gaps, getting-started instructions, and ship-log entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jessepinkman9900/claude-second-brain/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 jessepinkman9900/claude-second-brain --skill update-docs
Clone the repo
git clone --depth 1 https://github.com/jessepinkman9900/claude-second-brain

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/jessepinkman9900/claude-second-brain/update-docs.svg)](https://agentmods.dev/skills/jessepinkman9900/claude-second-brain/update-docs)
Your own site
<a href="https://agentmods.dev/skills/jessepinkman9900/claude-second-brain/update-docs"><img src="https://agentmods.dev/badge/skills/jessepinkman9900/claude-second-brain/update-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 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 $0.00062 $0.00896
Opus 5 $0.00031 $0.00448
Sonnet 5 $0.00012 $0.00179
Haiku 4.5 $0.00006 $0.00090

Measured 7d ago against content hash 7c487d1d502f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/update-docs

Audits the docs site for two things: features that shipped but aren't documented yet, and ship log versions that are missing or incomplete. Proposes all changes and waits for user approval before writing anything.

Steps

Run each step in order.


Step 1 — Gather current state

Run all of these in parallel:

# Commits on this branch not in main
git log main..HEAD --oneline

# All changed files vs main
git diff main...HEAD --stat

# Current package.json version
cat package.json | grep '"version"'

Also read:

  • docs/pages/ship-log.mdx — to find the latest documented version
  • docs/pages/getting-started.mdx — to check if CLI prompts/options are current
  • vocs.config.ts — to see what pages exist in the sidebar

Glob docs/pages/**/*.mdx to get the full list of doc pages.


Step 2 — Identify docs gaps

Compare the commits and changed files from Step 1 against the existing doc pages.

For each significant change (new CLI flag, new prompt, new skill, new remote option, new behavior), ask:

Is this change documented in any page under docs/pages/?

List every gap as:

GAP: <what changed> — not covered in docs

Also check getting-started.mdx for accuracy:

  • Does the CLI prompts list match the current wizard sequence?
  • Are all remote options mentioned?

Step 3 — Identify missing ship log entries

Read docs/pages/ship-log.mdx and find the latest version recorded.

Compare against package.json version. If the current version is higher than the latest ship log entry, it is missing.

Also check: does each existing entry accurately reflect what actually shipped? Look at the commits grouped by version tag (git log --oneline --decorate) and flag any entries that are incomplete or say "maintenance release only" when they contain real changes.

List each gap as:

MISSING: ship log entry for vX.Y.Z
INCOMPLETE: vX.Y.Z entry — missing: <what's not captured>

Step 4 — Propose changes

Present a consolidated proposal to the user:

Read the full file on GitHub · 132 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. 7d ago First seen · 132 lines · 62 tokens per session scan A 7c487d1d502f

Subscribe to this mod's changes

update-docs is a skill published in the GitHub repository jessepinkman9900/claude-second-brain (47 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 896 once invoked, about $0.0003 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

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

waku-computer-use

Control local Mac apps through Waku Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.

egoist/waku · 37 tokens

kmd-ingest

The write protocol for a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern) — personal or shared. Use for EVERY write into the KB — distilling a new or scraped source, promoting a finished artifact/report/lesson into the KB, filing a durable learning, insight, or query answer, or correcting/updating…

yasik/kmd · 135 tokens

kmd-lint

Health check for a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern) — personal or shared. Use whenever asked to lint, audit, check, review, or clean up a KB, on any scheduled hygiene/maintenance run, or when KB quality is in doubt (stale pages, contradictions, broken links, unprocessed sources…

yasik/kmd · 102 tokens

loredex-agent-ops

Manage an agent-ops dex — an agency's client fleet (Manager ▸ Client ▸ Pipeline/Agent ▸ Stage). Use when the user wants to add a client, pipeline, agent, or stage; tag clients; generate a client's MCP/plugin tooling from workspace.yml; or check fleet health. Requires a dex created with loredex init --type agent-ops.

ahmedtawfeeq1/loredex · 84 tokens

loredex

Overview and writing conventions for loredex. Use this as the fallback when the user's intent doesn't map to one specific loredex action, and always follow its frontmatter convention when writing research/findings/analysis markdown in a loredex-registered project. For a specific action, prefer the dedicated skill …

ahmedtawfeeq1/loredex · 104 tokens