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 a275618631/codex-antigravity-collaboration --skill mac-healthgit clone --depth 1 https://github.com/a275618631/codex-antigravity-collaborationWrote 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/a275618631/codex-antigravity-collaboration/mac-health)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/mac-health"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/mac-health/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/a275618631/codex-antigravity-collaboration/mac-health"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/mac-health.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 | $0.00076 | $0.01447 |
| Opus 5 | $0.00038 | $0.00724 |
| Sonnet 5 | $0.00015 | $0.00289 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade B, and why
mac-health 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 11d 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.
| **PROHIBITED** | 關閉 SIP / Gatekeeper、`sudo rm`、刪除 Keychain、手動 kill 系統核心 Daemon | **永久禁止!** | How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mac-health 技能指引 (Agent Skill Guide)
本技能規範 AI Agent 如何使用 diagnose.py、optimizer.py、compare.py 進行嚴謹、客觀、不誇大結論的 macOS 系統健康診斷與改善閉環。
1. 核心分析與判斷準則 (RCA Calibration Principles)
- 嚴格分級分類:
CONFIRMED BOTTLENECK:必須有明確、充分且不可辯駁的實質證據(例如:Critical 記憶體壓力且 Free < 20%、CPU 持續 > 85% 且特定進程獨佔、SSD 可用空間 < 15GB)。LIKELY CONTRIBUTOR:指標處於 Warning 且有單一巨量進程(> 2GB RAM / > 50% CPU)。ATTENTION:歷史 Swap 較高、短暫 I/O 觀測較忙、或 Memory Free 位於 30%~40% 邊界但無失控進程。NORMAL:指標處於安全區間。UNKNOWN:無法確定或無足夠權限取得之數據。
- Top Process 語意修正 (Notable != Problem):
- 單一 WebKit / 瀏覽器進程使用 500MB ~ 1.2GB RAM 屬於現代多工作瀏覽器分頁之常見正常負載,標記為
Notable process,嚴禁直接判定為卡頓主因或問題進程。 - 嚴禁直接建議終止 WebKit raw PID(例如禁止
kill PID 82252)。建議優先順序:1. 使用者自行檢視分頁並關閉不需要的分頁;2. 瀏覽器若持續卡頓建議正常重啟瀏覽器;3. 只有確認失控且獲明確核准才進行進程終止。
- 單一 WebKit / 瀏覽器進程使用 500MB ~ 1.2GB RAM 屬於現代多工作瀏覽器分頁之常見正常負載,標記為
- Swap 歷史語意:
- 歷史累積 Swap 高(如 20 GB)但當前即時 Memory Pressure 處於 Normal/穩態時,僅為
Historical memory pressure evidence或ATTENTION,不得直接宣稱為「當前已確認瓶頸」。
- 歷史累積 Swap 高(如 20 GB)但當前即時 Memory Pressure 處於 Normal/穩態時,僅為
- 重新啟動 Mac 語意修正:
- 重開機分類為
Low-cost troubleshooting / reset step。 - 禁止宣稱「徹底恢復流暢度」、「恢復出廠狀態」或「一定能改善」。
- 建議措辭:「如果目前仍有明顯卡頓,可在工作告一段落後正常重新啟動,作為低風險排查步驟;重啟會重置目前程序與 Swap 狀態,但不能保證根本問題消失。」
- 重開機分類為
- 預期效益措辭嚴謹:
- 優先使用「可能降低 Memory Pressure」、「可能釋放約 X MB process RSS」、「可能有助於改善反應速度」,禁止無證據承諾百分比或系統一定變快。
- 保守 Optimization Gate:
- 若
Confirmed bottleneck = None,預設回覆 「目前不需要立即修改系統。」,不為了交差而硬生產生優化動作。
- 若
2. Agent 標準輸出順序
未找到 Confirmed Bottleneck 時,必須優先明確宣告無確認瓶頸,接著條列各項指標:
Mac Health 診斷與分析報告
────────────────────────
Confirmed bottleneck:
None (目前沒有已確認的效能瓶頸)
Likely contributor:
None
Attention:
• Memory: 歷史 Swap 累計較高 (X GB),當前 derived pressure 位於 warning 邊界 (Free: Y%)。無單一失控進程。
Normal:
• CPU (即時使用率 X%,負載正常)
• Disk capacity (剩餘 X GB, 空間充足)
• Disk I/O observation (抽樣讀寫平穩)
• Thermal (溫度正常,無熱降頻)
• Spotlight (索引待機正常)
Notable processes:
• com.apple.WebKit.WebContent (PID: X, 650 MB) — 屬於現代多工作網頁常見佔用,未確認異常。
Recommendation:
目前不需要立即修改系統。
若實際仍感到卡頓,可先檢視並關閉確定不需要的瀏覽器分頁;若卡頓持續,可於工作告一段落後正常重新啟動 Mac 作為低風險排查步驟。
3. 安全操作分級 (Safety Levels)
What ships with it
21 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.
- compare.py 2.1 KB runs code
- diagnose.py 3.7 KB runs code
- docs/FUTURE_WORK.md 679 B
- docs/SAFETY.md 1.9 KB
- mac_health/__init__.py 116 B runs code
- mac_health/collectors.py 11 KB runs code
- mac_health/comparator.py 6.2 KB runs code
- mac_health/mole_adapter.py 8.0 KB runs code
- mac_health/optimizer.py 11 KB runs code
- mac_health/parsers.py 13 KB runs code
- README.md 5.8 KB
- tests/fixtures/df.txt 175 B
- tests/fixtures/iostat.txt 164 B
- tests/fixtures/memory_pressure.txt 110 B
- tests/fixtures/pmset_therm.txt 146 B
- tests/fixtures/power.json 423 B
- tests/fixtures/ps_cpu.txt 665 B
- tests/fixtures/swapusage.txt 80 B
- tests/fixtures/vm_stat.txt 869 B
- tests/test_diagnose.py 12 KB runs code
- tests/test_live_workloads.py 4.7 KB runs code
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.
- 11d ago First seen · 79 lines · 76 tokens per session scan B 33120a7af0fb
mac-health is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (8 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,447 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
aria
Designs the data model, API contracts, and structural foundation of the system.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".