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 WiseWong6/wise-skills --skill optimize-system-performancegit clone --depth 1 https://github.com/WiseWong6/wise-skillsWrote 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/wisewong6/wise-skills/optimize-system-performance)<a href="https://agentmods.dev/skills/wisewong6/wise-skills/optimize-system-performance"><img src="https://agentmods.dev/badge/skills/wisewong6/wise-skills/optimize-system-performance.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 13 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 25 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 31 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00094 | $0.01959 |
| Opus 5 | $0.00047 | $0.00979 |
| Sonnet 5 | $0.00019 | $0.00392 |
| Haiku 4.5 | $0.00009 | $0.00196 |
Grade A, and why
optimize-system-performance scanned grade A with 0 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize System Performance
Use a diagnose-first workflow. The default mode is read-only: capture a baseline, explain the causes in plain Chinese, show a short low-risk cleanup choice, then wait for the user before any cleanup. Treat this as a diagnosis and decision skill, not an automatic cleaner.
Safety Rules
- Default actions must be L0/L1 only: low-permission sampling, Chinese explanation, and cleanup recommendations.
- Do not use
sudo, elevated PowerShell, reboot, log out, clear caches, delete configs, disable startup items, unload plists, edit registry, change services, change scheduled tasks, or force-kill processes by default. - Do not stop browser main processes, remote control, VPN/proxy, sync drives, input methods, security software, enterprise management, meeting software, IDEs, Docker/VMs, Codex/Claude sessions, or local business services unless the user confirms that specific high-risk target after seeing the risk.
- Batch cleanup is allowed only for the report's explicit low-risk cleanup list after the user confirms a simple choice such as
清理低风险项. Never include protected, ambiguous, startup, service, Docker/VM/browser/IDE, or business-service targets in that batch. - When cleanup is confirmed, use only gentle user-process termination: macOS
kill -TERM <pid>; WindowsStop-Process -Id <pid>without-Force. If it fails, report it and stop. - Deep forensics are opt-in only. Before any high-risk tool, read the relevant reference and explain use, risk, permissions, duration, artifacts, and low-permission alternatives.
- For macOS deep forensics, run a command-path preflight first. Prefer system absolute paths such as
/usr/bin/sampleand/usr/sbin/spindump; never assume a bare command is the Apple tool because Python, Homebrew, or third-party installs may shadow it inPATH. - Default snapshots store executable/process names rather than full process arguments. Full command-line capture can expose tokens, paths, URLs, and business context, so treat it as opt-in deep inspection.
- Redact sensitive text in user-facing reports. Keep snapshot paths visible so the user can decide whether to delete them.
- Make decision ownership explicit but simple: the agent explains evidence and tradeoffs; the user can choose
清理低风险项or只观察. High-risk targets still need specific confirmation.
What ships with it
10 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.
- LICENSE 1.0 KB
- README.md 473 B
- references/deep-forensics-macos.md 2.0 KB
- references/deep-forensics-windows.md 1.4 KB
- references/platform-mapping.md 1.5 KB
- references/report-template.zh.md 2.5 KB
- scripts/capture_macos_snapshot.sh 17 KB runs code
- scripts/capture_windows_snapshot.ps1 7.7 KB runs code
- scripts/compare_snapshots.py 25 KB runs code
- scripts/normalize_snapshot.py 1.7 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.
- 8d ago First seen · 112 lines · 94 tokens per session scan A 320ce90d4e76
optimize-system-performance is a skill published in the GitHub repository WiseWong6/wise-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 1,959 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.