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 EZotoff/ez-omo-config --skill cleanup-disciplinegit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/ezotoff/ez-omo-config/cleanup-discipline)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/cleanup-discipline"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/cleanup-discipline/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/ezotoff/ez-omo-config/cleanup-discipline"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/cleanup-discipline.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 | $0.00074 | $0.01676 |
| Opus 5.5 | $0.00030 | $0.00670 |
| Sonnet 5.5 | $0.00015 | $0.00335 |
| Haiku 4.5 | $0.00007 | $0.00168 |
Grade B, and why
cleanup-discipline scanned grade B 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 27d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Outstanding operator actions (sudo commands, aggressive-prune hit-lists) as a copy-paste block. How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup Discipline
Phase 0 — Scope and authority
Establish from the operator, before proposing anything:
- What is fair game (e.g. "benchmark runs may be deleted" vs "regular sessions are archived and kept"). Ambiguity here is the #1 source of wrong deletions.
- Archive policy: which classes get archived-before-delete vs deleted outright. If the operator says "don't archive X", still capture small result artifacts (metrics, summaries) — bulk and results are different things.
Phase 1 — Survey (read-only, parallel)
df -hfirst; every later number is relative to it.- Layered
du -xh --max-depth=1 | sort -rh— root, then drill the top entries.-xto stay on one filesystem. - Close the ledger. Your itemized total must ≈
dfused. If it doesn't, you are blind to something: non-rootducannot see root-only dirs — check/var/lib/docker(docker system df),/var/lib/containers, reserved blocks, andlsof +L1for deleted-but-held-open files. (Real case: 160G of Docker invisible to a non-root survey made a report 45% wrong.) - Re-scan on multi-day campaigns — caches regrow and new runs land between passes. Diff against the previous scan before re-proposing.
Phase 2 — Classify every candidate
| Class | Examples | Rule |
|---|---|---|
| Regenerable cache | uv/npm/pip caches, HF cache, torch extensions | Prefer the tool's own clean (uv cache clean, docker system prune) over rm |
| Redundant copy | zips with extracted copies, shadow caches | Verify redundancy before believing it (Phase 3) |
| Result artifacts | metrics, reports, transcripts | Capture (Phase 4), then bulk is deletable |
| Runtime-tracked | plugin installs, patched builds, service dirs | Default: do not touch — see guard below |
| Active | running daemons' dirs, in-progress runs | Off-limits — check mtimes, pgrep, docker ps first |
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.
- 27d ago First seen · 77 lines · 74 tokens per session scan B ffabfa853ead
cleanup-discipline is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,676 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
refit
Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, friction reports, logs, and plan notepads. Every finding lands on the surface that owns the fix (deterministic check, steering volume, tooling, or information access); nothing is written without user approval.
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
whendone-plus
Automatically notify the user when long-running terminal commands finish (npm test, docker build, git push, etc.). The agent monitors command execution and sends a desktop notification on completion if the command ran longer than threshold (default 10s). Use when user asks to "notify me when done", "desktop…
hatch3r-cli-toolbox
Category-indexed reference for 34 specialist CLI tools beyond the always-on five (ripgrep, jq, gh, fd, fzf). Use to pick the right tool for HTTP clients, ai-chat, structural-search, sed-style edits, data ops, browser automation, container ops, and more.
armada-verification
Mandatory pre-completion verification and evidence checklist before reporting done.
armada-resume
Resume a killed or interrupted armada session. Use on session start or when nextAction is non-empty. Triggers on: resume, reconcile, killed session, /armada-resume.