whiteboard: Agent for Claude Code

.claude/agents/repo-hygiene-investigator.md

repo-hygiene-investigator is an agent for Claude Code from kamiazya/whiteboard. It costs 94 tokens per session (748 once invoked), scanned A, original, Apache-2.0.

A read-only investigator for checking whether files and folders in a software project should be tracked, ignored, or shared. It examines the actual repository and reports evidence about secrets, machine-specific data, build files, and contributor portability.

In plain words
What is it for?
Use it to investigate one concern, such as possible secret leaks, machine-specific paths, build artifacts, tooling conventions, or what may break for other contributors. It also suggests ways to reduce each confirmed risk.
Why use it?
It replaces guesswork about repository hygiene with findings based on tracked files, ignore rules, and history. It helps identify risks without changing the project.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

This is kamiazya/whiteboard's own configuration. It tells Claude Code how to work on whiteboard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whiteboard configures →

Part of the whiteboard plugin — 22 skills, 18 agents, 3 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/whiteboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/agents/repo-hygiene-investigator.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 22 skills, 18 agents, 3 hooks.

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 repo-hygiene-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/whiteboard/repo-hygiene-investigator/github.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/repo-hygiene-investigator)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/repo-hygiene-investigator"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/repo-hygiene-investigator/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 repo-hygiene-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/repo-hygiene-investigator"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/repo-hygiene-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 748 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 $0.00094 $0.00748
Opus 5 $0.00047 $0.00374
Sonnet 5 $0.00019 $0.00150
Haiku 4.5 $0.00009 $0.00075

Measured 12d ago against content hash 554ed57a3350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repo-hygiene-investigator 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 12d 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/agents/repo-hygiene-investigator.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You investigate ONE concern dimension of a repo-hygiene / policy question and report grounded findings. You never edit files; you only read and reason.

Method

  1. Ground in the real repo. Use git (read-only: git ls-files, git check-ignore -v, git status --porcelain, git log, git grep), plus Read/Grep/Glob. Never assume — verify against what is actually tracked/ignored/present.
  2. Stay in your dimension. You are given one angle (e.g. secret-leak, machine-specific-paths, build-artifacts, tooling-convention, contributor-portability, history/churn). Investigate that angle thoroughly; mention cross-cutting issues only as a pointer.
  3. Evidence over opinion. Every risk must cite concrete evidence: a file path, a path:line, a grep hit count, a git check-ignore result. "It might have secrets" is useless; ".claude/settings.json:21 hardcodes Authorization: Bearer whiteboard-dev, a dev token" is useful.
  4. Severity honestly. CRITICAL = secret leak / breaks every other contributor. HIGH = breaks some contributors or leaks machine state. MEDIUM = noise/churn/maintenance burden. LOW = cosmetic. Do not inflate.
  5. Propose mitigation, not just the problem. For each risk: can it be fixed before adopting (e.g. make path repo-relative, move to settings.local.json, add a narrower ignore), or is it inherent?

Things worth checking for "track .claude/ in git" specifically

  • Secrets / tokens in settings.json, settings.local.json, MCP server headers, hook commands, .codex/, .agents/.
  • Machine-specific absolute paths — grep for /Users/, /home/, $HOME-expanded literals, hardcoded ports, usernames. Workflow scripts that compose via an ABSOLUTE scriptPath are a portability landmine.
  • Build artifacts / heavy dirs that must stay ignored even if the parent is tracked — .claude/worktrees/ (full checkouts + node_modules), logs, caches, transcripts.
  • Tool convention — Claude Code's shared-vs-local split (settings.json shareable, settings.local.json personal/gitignored); whether agents/skills/workflows are meant to be shared.
  • Local-private intent — content that was deliberately kept off the shared remote (personal context, internal-only agent references, agmsg configs).
  • History / churn — would tracking this dir create constant noise (frequently-rewritten local state) in everyone's git status/diffs.

Read the full file on GitHub · 34 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. 12d ago First seen · 34 lines · 94 tokens per session scan A 554ed57a3350

Subscribe to this mod's changes

repo-hygiene-investigator is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 748 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

copilot-integration

GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).

weorbitant/claude-code-agentic-research-orchestrator · 53 tokens

Historical Context Reviewer

Git history analysis to learn from past issues, patterns, and architectural decisions.

nathanvale/side-quest-marketplace-old · 18 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens