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 skills add Kevin-Liu-01/Agent-Broom --skill skillgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-BroomWrote 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/skills/kevin-liu-01/agent-broom/skill)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-broom/skill"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-broom/skill/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.
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-broom/skill"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-broom/skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.00397 |
| Opus 5 | $0.00044 | $0.00198 |
| Sonnet 5 | $0.00018 | $0.00079 |
| Haiku 4.5 | $0.00009 | $0.00040 |
Grade A, and why
agent-broom 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 10d 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.
What it actually says
Agent Broom
This skill is the memory hook. It exists so agents remember to run the CLI.
The deterministic cleanup behavior lives in bin/agent-broom, bin/ports,
bin/whoisonport, and lib/*.sh.
Start with the port checker surface when the user asks what is running or when a localhost port may be occupied:
bin/agent-broom ports --json
bin/agent-broom port <PORT> --json
bin/agent-broom ps --json
Run a dry-run audit first:
bin/agent-broom audit
Record long-running commands you start:
bin/agent-broom add --pid <PID> --kind dev --port <PORT> --purpose "<why>" -- <command>
Before ending the turn:
bin/agent-broom audit
Only act after reviewing the dry run:
bin/agent-broom kill <PORT|PID|RANGE>
bin/agent-broom kill --apply <PORT|PID|RANGE>
bin/agent-broom clean
bin/agent-broom clean --apply
bin/agent-broom stop --kill
bin/agent-broom artifacts --clean
bin/agent-broom devclean --apply
Never kill the editor, Codex, the user's shell, or shared MCP servers unless the script proves they are safe orphaned targets.
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.
- 10d ago First seen · 53 lines · 89 tokens per session scan A 5a9995f2c818
agent-broom is a skill published in the GitHub repository Kevin-Liu-01/Agent-Broom (5 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 397 once invoked, about $0.0004 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.
Other skills, from other repositories
vendo-setup
Install and configure Vendo (the embedded product agent) in a host repo. Use when asked to add Vendo to an app, run vendo init/doctor/sync, wire the Vendo handler or VendoProvider, or debug a Vendo install.
portless
Named HTTPS .localhost URLs with portless (v0.15.x). Eliminates port collisions, gives agents stable URLs, adds branch-named subdomains for git worktrees, LAN mode (--lan), and Tailscale sharing. Use when setting up a local dev environment or testing from phones and tablets on the same wifi. Do NOT use for production…
make-a-screen
Use when an answer about the connected product would land better as something the person can look at and use than as text you type out — a comparison, a trend, many rows, a thing they will come back to, or a thing they need to act on. Also use when they ask to change a screen they already have.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
cis-aws-compute-2.10
Ensure unused ENIs are removed.
cis-aws-compute-2.2.4
Ensure unused EBS volumes are removed.