A public-surface scanner that looks for sensitive identifiers in a repository's code, history, issues, pull requests, and forks.

It reports where such identifiers appear and whether they can be removed, without editing files, issues, pull requests, or history.

Internal account IDs, hostnames, resource IDs, and email addresses can expose useful information even when they are not passwords or other credentials.

repo-scrub — Skill for Claude Code and Codex by rjwalters/kicad-tools

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 rjwalters/kicad-tools --skill repo-scrub

Clone the repo

git clone --depth 1 https://github.com/rjwalters/kicad-tools

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-scrub/github.svg)](https://agentmods.dev/skills/rjwalters/kicad-tools/repo-scrub)

Your own site

<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-scrub"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-scrub/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-scrub"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-scrub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,122 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.05122
Opus 5.5	$0.00014	$0.02049
Sonnet 5.5	$0.00007	$0.01024
Haiku 4.5	$0.00003	$0.00512

Measured 8d ago against content hash 6222a5cebb2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-scrub 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 8d 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.

.agents/skills/repo-scrub/SKILL.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex form of the /repo:scrub command. Other commands appear as $repo-<verb> skills. Helper scripts and .claude/ paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.

$repo-scrub — Public-Surface Scrub

Answer one question the other hygiene commands don't: is there anything here that should not be public?

That gap matters most where agents author content continuously. An agent writing an issue, a runbook, or an incident write-up has no instinct for which identifiers are sensitive, and those artifacts are exactly the genre where account IDs, resource IDs, internal hostnames, and email addresses accumulate. None of it is a credential; all of it is useful to an attacker. The drift is slow and invisible, which is why it needs a check on a routine cadence rather than a person remembering to look.

This command reports. It never edits. Same posture as [[orphans]]: name the file, commit, issue, or PR and the class, and stop. Deleting an issue or rewriting history is irreversible and is an operator decision — and, as the removability section below explains, usually a less complete fix than the operator assumes.

Usage

$repo-scrub                      # This repo, default verbosity — credentials and live-at-HEAD findings
$repo-scrub --deep               # Add history-only and network-topology classes
$repo-scrub --owner <owner>      # Every public repo for an owner/org, enumerated from the forge
$repo-scrub --forks              # Also sweep the fork network (delegates to repo-scrub-forks.sh)
$repo-scrub --json               # Machine-readable findings

$repo-all runs the default form only — this repo, quiet verbosity, no forge enumeration and no fork sweep. The wide forms cost API calls and minutes, and belong in a deliberate invocation.

Read the full file on GitHub · 417 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.

8d ago First seen · 417 lines · 35 tokens per session scan A 6222a5cebb2f

Subscribe to this mod's changes

repo-scrub is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 5,122 once invoked, about $0.0001 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 2026-11-01.