all

all is a command for Claude Code from rjwalters/kicad-tools. It costs 30 tokens per session (5,585 once invoked), scanned A, original, MIT.

A complete repository-cleanup routine that checks code, public files, documentation, clutter, installed tools, and dependency freshness in a set order.

In plain words
What is it for?
Use it to run a routine hygiene pass across a repository or one folder, optionally reviewing each change or pruning extra files.
Why use it?
It brings common maintenance tasks together and applies low-risk fixes while asking before destructive or externally affecting actions.

Command for Claude Code

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/rjwalters/kicad-tools/all
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

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 all

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjwalters/kicad-tools/all.svg)](https://agentmods.dev/commands/rjwalters/kicad-tools/all)
Your own site
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/all"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/all.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,585 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 $0.00030 $0.05585
Opus 5 $0.00015 $0.02792
Sonnet 5 $0.00006 $0.01117
Haiku 4.5 $0.00003 $0.00558

Measured 5d ago against content hash 945bf2702064, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

all 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 5d 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/commands/repo/all.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/repo:all — The Whole Hygiene Pass

Run the full sequence of sensible repo work in one go: scan for problems, check the public surface for sensitive identifiers, bring the docs back in line with reality, tidy filesystem clutter, refresh installed tool packages, report on third-party dependency currency, and land back on a clean baseline. This is the umbrella command — it orchestrates the other /repo:* commands in a deliberate order, applying each one's safe fixes by default and keeping the same safety gates on destructive steps that each uses on its own.

It deliberately does not launch cloud dev sessions ([[remote]]) — that provisions paid infrastructure and is never part of a routine hygiene pass. And it only ever runs [[deps]]' read-only half (--check): scaffolding Dependabot config, flipping repository flags, and merging bot PRs all stay behind /repo:deps' own confirmations.

Usage

/repo:all                      # Full repo — apply safe fixes across stages, report as you go
/repo:all --ask                # Confirm findings before applying at every stage
/repo:all packages/core        # Scope the read-only scans to one subtree
/repo:all --prune              # Also delete confirmed-safe branches/worktrees (passed to reset, after the loss check)
/repo:all --caches             # Also clear regenerable caches in the Tidy stage (passed to tidy; off by default)

The optional path argument scopes the scanning stages ([[audit]]) the same way it does for those commands. Stages that act on global git or filesystem state ([[tidy]], [[reset]]) always operate on the whole repo.

Stages

Run these in order. Each stage applies its safe, reversible fixes by default and reports them; irreversible removals (Tidy's ASK items, Reset's branch/worktree/stash deletion) still require explicit approval and pass the permanent-loss check — they are never chained silently. Under --ask, every stage reverts to report-first: show what was found and get a yes before acting. If the user declines a stage, note it and continue to the next.

Read the full file on GitHub · 425 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. 5d ago First seen · 425 lines · 30 tokens per session scan A 945bf2702064

Subscribe to this mod's changes

all is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 5,585 once invoked, about $0.0002 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.