revise-all-docs

revise-all-docs is a command for Claude Code from taylorleese/claude-toolz. It costs 18 tokens per session (637 once invoked), scanned A, original, MIT.

A command that reviews the current coding session and updates CLAUDE.md, README.md, and docs Markdown files with useful project knowledge.

In plain words
What is it for?
Use it to record development lessons in the appropriate documentation, including contributor guidance, setup details, and user-facing instructions.
Why use it?
It prevents helpful discoveries about commands, testing, configuration, architecture, and warnings from being lost after the session.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the revise-all-docs plugin — 1 skill, 2 commands shipped together

Good fit Use it to record development lessons in the appropriate documentation, including contributor guidance, setup details, and user-facing instructions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/taylorleese/claude-toolz/revise-all-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.

Clone the repo
git clone --depth 1 https://github.com/taylorleese/claude-toolz

Made for: Claude Code.

Or install revise-all-docs, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 revise-all-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/taylorleese/claude-toolz/revise-all-docs/github.svg)](https://agentmods.dev/commands/taylorleese/claude-toolz/revise-all-docs)
Your own site
<a href="https://agentmods.dev/commands/taylorleese/claude-toolz/revise-all-docs"><img src="https://agentmods.dev/badge/commands/taylorleese/claude-toolz/revise-all-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 revise-all-docs

Your own site · 80×15
<a href="https://agentmods.dev/commands/taylorleese/claude-toolz/revise-all-docs"><img src="https://agentmods.dev/badge/commands/taylorleese/claude-toolz/revise-all-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 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 $0.00018 $0.00637
Opus 5 $0.00009 $0.00318
Sonnet 5 $0.00004 $0.00127
Haiku 4.5 $0.00002 $0.00064

Measured 9d ago against content hash b17fa65965d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

revise-all-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 9d 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.

plugins/revise-all-docs/commands/revise-all-docs.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review this session for context worth recording in the project's docs. Update CLAUDE.md, README.md, and any docs//*.md** files with what would help future contributors and Claude sessions.

Step 1: Reflect

What context was missing or out-of-date this session? Capture:

  • Bash commands used or discovered (build, test, lint, deploy, debug)
  • Code style patterns enforced
  • Testing approaches that worked
  • Environment / config quirks
  • Warnings or gotchas
  • User-facing changes (install / quickstart / public commands) — these belong in README, not CLAUDE.md
  • Architecture or contributor-guide drift — these belong in docs/

Step 2: Delegate CLAUDE.md updates

Invoke the claude-md-management:revise-claude-md skill via the Skill tool. It owns all CLAUDE.md and .claude.local.md updates. Wait for it to finish before continuing.

Step 3: Discover other docs

# Project-level READMEs (skip vendored / build dirs)
find . -name "README.md" -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/venv/*" -not -path "*/.venv/*" -not -path "*/dist/*" 2>/dev/null

# All markdown under docs/
find docs -name "*.md" 2>/dev/null

If neither exists, skip to Step 5 with an empty change set.

Step 4: Categorize each candidate addition

For each piece of context surfaced in Step 1, decide where it belongs:

Destination What goes there
CLAUDE.md (handled in Step 2 — skip if Step 2 already covered it)
README.md User-facing onboarding, install, quickstart, public command surface, badges, top-level project description
docs/<file>.md Deeper how-to, architecture, contributor guides — match each addition to the most topical existing file

Do not create new doc files. Only update existing ones. If a learning doesn't fit any existing file, leave it out and call that out explicitly to the user.

One line per concept — same density as revise-claude-md. No filler.

Step 5: Show & apply

Group proposed changes by file. For each file that receives updates, show:

Read the full file on GitHub · 63 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. 9d ago First seen · 63 lines · 18 tokens per session scan A b17fa65965d6

Subscribe to this mod's changes

revise-all-docs is a command published in the GitHub repository taylorleese/claude-toolz (3 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 637 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.