system-performance-guardrail

77 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By jpantsjoha/ai-native-developer-experience (GitHub) · coding · 13 stars · scanned at commit c412b2c

Measure, root-cause, fix, verify and record performance contention on a developer machine: cloud-sync daemons (iCloud Drive, OneDrive, Dropbox, Google Drive), file indexers, AI-tool MCP server fleets, and automation browsers left behind by tests and browser skills. Trigger when the machine is slow, apps freeze, browser or MCP tool calls time out, load exceeds the core count, or before and after any UI/UX/performance test run. Includes the L0–L4 optimisation scale and the test-hygiene contract.

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 3 places.

skills/system-performance-guardrail/scripts/perf-guardrail.sh, line 84printf ' npm/npx exec %s | node/uv MCP servers %s | disposable automation browsers+drivers %s | AI CLI sessions %s\n' "$npm" "$mcp" "$auto" "$ai"
skills/system-performance-guardrail/scripts/perf-guardrail.sh, line 108ps -axo pid=,ppid=,etime=,rss=,args= | $G -E ' (npm exec|npx |node [^ ]*(mcp|toolbox|server\.js)|uvx? .*(mcp|server\.py))' | $G -v "$G" | while read pid ppid et
skills/system-performance-guardrail/scripts/perf-guardrail.sh, line 109echo " Rule: an AI CLI run that spawns more than a handful of servers is a config problem (npx @latest re-resolves every start). Count per run, then remove wha

Connects to the internet

The author does not mention this.

Found in 1 place.

.kimi-plugin/plugin.json, line 36"skillInstructions": "Kimi Code tool mapping for this plugin's skills:\n\n- When a skill says to ask the user, ask clarifying questions, or present multiple-cho

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed. Expected for a coding skill.

Found in 2 places.

hooks.json, line 9"command": "\"${CLAUDE_PLUGIN_ROOT}/hooks/session-start\"",
hooks/hooks.json, line 9"command": "\"${CLAUDE_PLUGIN_ROOT}/hooks/session-start\"",

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'system-performance-guardrail' ] || [ -L ~/.agents/skills/'system-performance-guardrail' ]; then echo 'A skill folder named system-performance-guardrail already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/jpantsjoha/ai-native-developer-experience' "$d" && git -C "$d" checkout --quiet 'c412b2ce7b44101cfdef08860396a53cee7a5fe4' -- 'skills/system-performance-guardrail' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/system-performance-guardrail' ~/.agents/skills/'system-performance-guardrail' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'system-performance-guardrail' ~/.claude/skills/'system-performance-guardrail' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for jpantsjoha/ai-native-developer-experience shows the score of its lowest-scoring skill.

SkillTrust badge for jpantsjoha/ai-native-developer-experience

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/jpantsjoha/ai-native-developer-experience.svg)](https://zalavijaysinh.github.io/skilltrust/repos/jpantsjoha/ai-native-developer-experience/)

Score history

Date	Version	Score
2026-11-12	`c412b2c`	77
2026-11-08	`f3da50b`	77