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/lifedever/skills-plugin/mac-cleanup-memorynpx skills add lifedever/skills-plugin --skill mac-cleanup-memorygit clone --depth 1 https://github.com/lifedever/skills-pluginWrote 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/lifedever/skills-plugin/mac-cleanup-memory)<a href="https://agentmods.dev/skills/lifedever/skills-plugin/mac-cleanup-memory"><img src="https://agentmods.dev/badge/skills/lifedever/skills-plugin/mac-cleanup-memory.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 | $0.00207 | $0.02413 |
| Opus 5 | $0.00103 | $0.01207 |
| Sonnet 5 | $0.00041 | $0.00483 |
| Haiku 4.5 | $0.00021 | $0.00241 |
Grade B, and why
mac-cleanup-memory scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| "run purge" / "执行 purge" | Run `sudo purge` (user enters their own password) | How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mac-cleanup-memory
A skill for diagnosing macOS memory state — diagnostic-only mode. Never proactively kills any process.
Execution Flow After Trigger
Step 1: Run the scan script
bash "${CLAUDE_SKILL_DIR}/scan.sh"
The script:
- Prints a full Markdown report to stdout
- Tees it to
~/Downloads/mac-cleanup-memory-<timestamp>.md - Exits 0 on success, 1 on failure with diagnostics written to stderr
Step 2: Present the report
Paste the stdout Markdown content to the user verbatim. You may add one or two observations at the end pointing out the most notable items, but:
- Never modify / fabricate / omit any numbers in the report (RSS, PID, pressure level)
- Never add candidates from your own
ps aux | grepthat the script didn't surface - Never add "I suggest killing X" to the report — that's the user's call
Step 3: Wait for user instruction
| User reply | Action |
|---|---|
| No reply / "ok" / "got it" | Do nothing |
kill <PID> or kill <PID1> <PID2> |
Follow the [Kill Safety Protocol], one PID at a time |
| "run purge" / "执行 purge" | Run sudo purge (user enters their own password) |
| "kill all WeChat" / "把微信全杀了" | Must list every PID + command for confirmation first — never use pkill/killall directly |
| "clean up everything" / vague instruction | Ask back: "Which specific PIDs?" |
🛡️ Kill Safety Protocol (core, bolded)
For each kill, walk through all the steps one PID at a time. If any step fails, abort that PID (other PIDs are unaffected).
0. Active session strong protection (highest priority, added 2026-05-13)
Each process in the scan.sh report carries a status tag:
- 🟢 IDE — IDE/editor associated (VSCode/Cursor/JetBrains/Xcode/Sublime child process, or path contains
vscode/extensions/anthropic.claude-code) - 🟢 TTY — has a controlling terminal (the user is watching it in a terminal tab)
- 🟡 new — etime < 30 minutes
- 🔴 orphan — true zombie (CLI child class with PPID=1)
- — — normal
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 195 lines · 207 tokens per session scan B e091b1364f22
mac-cleanup-memory is a skill published in the GitHub repository lifedever/skills-plugin (11 stars, last pushed 13d ago), licensed MIT. It adds 207 tokens to every session and 2,413 once invoked, about $0.0010 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…