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 rianvdm/product-ai-public --skill diagnosing-mac-performancegit clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/diagnosing-mac-performance)<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/diagnosing-mac-performance"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/diagnosing-mac-performance/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/rianvdm/product-ai-public/diagnosing-mac-performance"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/diagnosing-mac-performance.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 | $0.00089 | $0.01776 |
| Opus 5 | $0.00044 | $0.00888 |
| Sonnet 5 | $0.00018 | $0.00355 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade D, and why
diagnosing-mac-performance scanned grade D with 2 findings 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.
| mds / mds_stores / mdworker | <5% each | >20% or many workers | Spotlight indexing. Usually transient after updates. `sudo mdutil -i off /` to pause if urgent. | Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Never suggest `sudo rm -rf` on system directories How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing Mac Performance Issues
When to Use
- User says their Mac feels slow, laggy, or unresponsive
- User asks what's consuming CPU, memory, or battery
- User reports fans running loud or machine running hot
- Proactive check during long sessions if the user mentions sluggishness
Steps
-
Snapshot system state — run these in parallel:
# Top processes by CPU ps -eo pid,pcpu,pmem,comm -r | head -25 # System overview (load avg, memory, swap) top -l 1 -n 1 -stats pid,command,cpu | head -10 # Memory pressure and swap sysctl vm.swapusage && memory_pressure -
Triage into CPU-bound vs memory-bound:
- CPU-bound: One or more processes above 30% CPU. Identify and investigate.
- Memory-bound: Swap used > 2 GB, compressor > 4 GB, or "Pages free" under 10,000. Even if no single process is hot, the system spends CPU on compression/decompression and swap I/O.
- Both: Common. A runaway daemon often causes memory pressure too.
-
For CPU hogs — identify the category:
Process type Normal range Investigate if Common fix WindowServer 10-20% >35% sustained Usually driven by another app doing excessive redraws. Fix the other app. contactsd / AddressBookManager <2% >10% Stuck sync loop. Check error logs, disable problematic account sync (Gmail CardDAV is a known offender). mds / mds_stores / mdworker <5% each >20% or many workers Spotlight indexing. Usually transient after updates. sudo mdutil -i off /to pause if urgent.kernel_task varies >200% Thermal throttling. Not fixable via software — machine needs cooling. nsurlsessiond / cloudd <5% >15% iCloud sync stuck. Check System Settings > Apple ID > iCloud. trustd <1% >10% Certificate validation loop. Often clears on reboot. Electron apps (Discord, Slack, VS Code, Windsurf) 2-5% each >15% Restart the app. Electron apps leak memory over time.
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 · 111 lines · 89 tokens per session scan D 757838e857e7
diagnosing-mac-performance is a skill published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 1,776 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.