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 skills/markmhendrickson/ateles/disk-cleanupnpx skills add markmhendrickson/ateles --skill disk-cleanupgit clone --depth 1 https://github.com/markmhendrickson/atelesWhat 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 | $0.00055 | $0.01015 |
| Opus 5 | $0.00028 | $0.00508 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade C, and why
disk-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 3d 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.
| CloudKit | `rm -rf ~/Library/Caches/CloudKit/*` | How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disk Cleanup
Core behavior
- Run analysis to discover candidates
- Surface candidates by tier (highest leverage, safest first)
- Ask for approval before executing each tier
- Execute only approved tiers; then present the next tier
Step 1: Run analysis
./execution/scripts/preview_deletions.sh
du -sh ~/Library/Caches/* 2>/dev/null | sort -hr | head -25
du -sh ~/.npm ~/Library/Application\ Support/Google/Chrome ~/Library/Containers/com.docker.docker/Data 2>/dev/null
docker system df 2>/dev/null
Step 2: Present tiers and ask for approval
Present each tier with estimated size and risk. Wait for user approval before executing. Only proceed to the next tier after the current one is approved and run.
Tier 1 — Automated script (zero risk)
Script clears Homebrew, pip, npm, old logs, trash. All reproducible.
Approve Tier 1? (yes/no)
If approved:
./execution/scripts/disk_cleanup.sh --yes
Tier 2 — Large app caches (zero risk, ~3–7 GB)
Apps re-download as needed. Present current sizes from analysis, then ask approval.
| Cache | Command |
|---|---|
| CloudKit | rm -rf ~/Library/Caches/CloudKit/* |
| Telegram | rm -rf ~/Library/Caches/ru.keepcoder.Telegram/* |
| OpenAI Atlas | rm -rf ~/Library/Caches/com.openai.atlas/* |
| npm | npm cache clean --force |
Approve Tier 2? (yes/no)
Tier 3 — Medium app caches (zero risk, ~2–3 GB)
| Cache | Command |
|---|---|
| Mozilla | rm -rf ~/Library/Caches/Mozilla/* |
| Granola | rm -rf ~/Library/Caches/com.granola.app.ShipIt/* |
| Brave | rm -rf ~/Library/Caches/BraveSoftware/* |
| Yarn | rm -rf ~/Library/Caches/Yarn/* |
rm -rf ~/Library/Caches/Google/* |
Approve Tier 3? (yes/no)
Tier 4 — Smaller app caches (zero risk, ~0.5–1 GB)
| Cache | Command |
|---|---|
| Ledger Live | rm -rf ~/Library/Caches/ledger-live-desktop-updater/* |
| node-gyp | rm -rf ~/Library/Caches/node-gyp/* |
| Loom | rm -rf ~/Library/Caches/loom-updater/* |
| Playwright | rm -rf ~/Library/Caches/ms-playwright |
| Loom ShipIt | rm -rf ~/Library/Caches/com.loom.desktop.ShipIt |
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.
- 3d ago First seen · 125 lines · 55 tokens per session scan C 4abc4261940b
disk-cleanup is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 1,015 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
10x-orchestrator
MANDATORY - The core brain of 10X Vibe Marketer. You are the autonomous CMO orchestrating a full marketing agency of 12 specialist departments. Load this skill for ANY marketing task - content creation, SEO, campaigns, strategy, research, analytics, outreach, social media, email, paid ads, branding, funnel…
10x-setup
First-time setup and initialization for 10X Vibe Marketer. Includes an interactive wizard that lets users choose their database, features, marketing focus, visual tools, and tracking preferences. Checks setup.log to determine if setup has already been completed. Run via /setup or auto-triggered on first use.
10x-visualizer
Generate visual marketing deliverables — strategy boards, funnel diagrams, flowcharts, journey maps, dashboards, and more — using TLDraw SDK (local .tldr files). Each department agent creates visuals for their own domain. Invoke with /report.
community-manager
Skill "community-manager" from OpenAnalystInc/Vibe-Marketer, covering community manager — 10x vibe marketer, identity, step-by-step execution, cli visual identity and expertise.
10x-research
The research orchestration engine for 10X Vibe Marketer. Powers multi-platform, real-time research across 13 platforms using Claude in Chrome and WebSearch/WebFetch. Spawns platform-specific research agents in parallel, consolidates findings through the research lead, and delivers actionable marketing intelligence.
affiliate-specialist
Skill "affiliate-specialist" from OpenAnalystInc/Vibe-Marketer, covering affiliate specialist — 10x vibe marketer, identity, step-by-step execution, cli visual identity and expertise.