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.
npx agentmods add commands/insight-services-apac/ingenious/janitorgit clone --depth 1 https://github.com/Insight-Services-APAC/ingeniousWrote 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.
[](https://agentmods.dev/commands/insight-services-apac/ingenious/janitor)<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/janitor"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/janitor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00339 |
| Opus 5 | $0.00000 | $0.00169 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
janitor 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 yesterday.
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.
What it actually says
Run code quality checks in parallel using Opus subagents and git worktrees. Fix all issues found—don't just report them.
Create a separate git worktree for each tool, spawn an Opus subagent per worktree, and merge all changes into the soca branch when complete.
Tools to run
/bandit— Python security linter/docstrings— Python docstring checker/mypy— Python type checker/radon— Python complexity metrics/vulture— Python dead code finder/audit— Dependency vulnerability scan/complexity— Code complexity analysis/jsdoc— JavaScript documentation checker/knip— JavaScript unused exports/dependencies/tsc— TypeScript compiler checks
Instructions
- Create a git worktree for each tool in a temp directory
- Launch all Opus subagents concurrently (one per tool/worktree)
- Each subagent must:
- Run its assigned tool
- Automatically fix every issue found (not just diagnose)
- Group fixes into small, logical commits with clear messages
- Wait for all subagents to complete
- Merge each subagent's commits into the
socabranch, preserving the small logical commits (rebase or cherry-pick as needed to maintain clean history) - Resolve any merge conflicts
- Clean up worktrees when finished
Important: The goal is a fully remediated codebase with a clean commit history, not a report. Take action on every finding.
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.
- yesterday First seen · 32 lines · 0 tokens per session scan A 047f3764bc0e
janitor is a command published in the GitHub repository Insight-Services-APAC/ingenious (24 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 339 tokens. 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 2026-09-04.
Other commands, from other repositories
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
manps
Inspect project health through mancode.
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
incident
把当前 session 中的故障排查 / Bug 修复过程蒸馏成故障复盘 (6 段: 现象/影响/根因/解决过程/改进/时间线).
cleanup
Run a systematic cleanup on the provided code to resolve smells, simplify complexity, and enforce best practices.