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.
git clone --depth 1 https://github.com/openshift-eng/ai-helpersWrote 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/openshift-eng/ai-helpers/cleanup)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/cleanup"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/cleanup/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/commands/openshift-eng/ai-helpers/cleanup"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/cleanup.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 | $0.00012 | $0.00997 |
| Opus 5.5 | $0.00005 | $0.00399 |
| Sonnet 5.5 | $0.00002 | $0.00199 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade C, and why
cleanup scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Only remove `.work/node-rpm/` if `vagrant destroy` succeeded (or no Vagrantfile was present). Delete all other locations with `rm -rf`. Report each deletion: How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
node-team:cleanup
Synopsis
/node-team:cleanup [--older-than N] [--dry-run]
Description
Removes local artifacts created by Node team plugins: triage reports, cloned repos, dist-git clones, Vagrant VMs, and cached roster data. Use this to reclaim disk space or to satisfy data purge requirements (DATA-05).
Options
| Flag | Default | Description |
|---|---|---|
--older-than N |
30 | Only remove triage directories older than N days |
--dry-run |
off | Show what would be removed without deleting |
Implementation
1. Discover artifacts
Scan for these locations relative to the current working directory and home:
| Location | Contents |
|---|---|
.work/node-cve/repos/ |
Shallow repo clones |
.work/node-cve/triage-YYYY-MM-DD/ |
CVE triage reports and analysis |
.work/node-bug/triage-YYYY-MM-DD/ |
Bug triage reports |
.work/node-rpm/ |
Dist-git clones and Vagrant VM |
~/.node-assistant/ |
Cached team roster JSON files |
For each location that exists, compute the size with du -sh.
2. Filter by age
For .work/node-cve/triage-*/ and .work/node-bug/triage-*/ directories,
parse the date from the directory name and skip directories newer than
--older-than days. The repos/, .work/node-rpm/, and ~/.node-assistant/
directories are always included (no age filter).
3. Show summary
Use $PWD for .work/ paths and $HOME for home directory paths so
the user sees resolved locations. Print a table:
Location Size Age
$PWD/.work/node-cve/repos/ 1.2G -
$PWD/.work/node-cve/triage-2026-05-01/ 45M 59 days
$PWD/.work/node-cve/triage-2026-06-15/ 52M 14 days (skipped, < 30 days)
$PWD/.work/node-bug/triage-2026-05-01/ 12M 59 days
$PWD/.work/node-rpm/ 380M -
$HOME/.node-assistant/ 128K -
Total to remove: 1.64G
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.
- 1mo ago First seen · 98 lines · 12 tokens per session scan C d136805da900
cleanup is a command published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 997 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
r
Resume the last handoff and carry on with the outstanding work.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.
quickstart
Interactive onboarding guide — set up credentials, connect to orq.ai, and learn every command and skill.