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/zhpeng24/devkit/mihomo-proxy-setupnpx skills add zhpeng24/devkit --skill mihomo-proxy-setupgit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00065 | $0.02999 |
| Opus 5 | $0.00032 | $0.01499 |
| Sonnet 5 | $0.00013 | $0.00600 |
| Haiku 4.5 | $0.00006 | $0.00300 |
Grade D, and why
mihomo-proxy-setup scanned grade D with 4 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 yesterday.
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.
A skill for installing and managing a **Mihomo-based proxy** in user-space. Supports Linux (systemd user services) and macOS (launchd agents). No root/sudo required. Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
with-proxy <cmd> — Run any command through proxy Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- [ ] **Remove config directories:** `rm -rf ~/.config/mihomo ~/.config/proxy` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [ ] **Controller reachable:** `curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:{{controller_port}}` How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mihomo Proxy Setup
A skill for installing and managing a Mihomo-based proxy in user-space. Supports Linux (systemd user services) and macOS (launchd agents). No root/sudo required.
When to Use
Trigger when the user asks to:
- Install a proxy / set up Mihomo / configure Clash subscription
- Add proxy wrappers for dev tools (Cursor, Claude, GitHub Copilot)
- Uninstall or clean up an existing Mihomo proxy setup
- Troubleshoot proxy connectivity issues
Architecture Overview
┌─────────────────────────────────────────────────┐
│ User Space │
│ │
│ ┌───────────┐ ┌──────────────────────────┐ │
│ │ Mihomo │◄──│ Clash Subscription YAML │ │
│ │ (daemon) │ │ + Local Overrides │ │
│ │ │ └──────────────────────────┘ │
│ │ mixed:7890│ │
│ │ ctrl:29090│──► MetaCubeXD Web UI │
│ └───────────┘ │
│ ▲ │
│ │ HTTP_PROXY / SOCKS5 │
│ ┌────┴──────────────────────────┐ │
│ │ Proxy Wrappers │ │
│ │ with-proxy <cmd> │ │
│ │ proxy-agent (Cursor) │ │
│ │ proxy-copilot (GH Copilot) │ │
│ │ proxy-claude (Claude CLI) │ │
│ └───────────────────────────────┘ │
│ │
│ Service Manager: │
│ Linux → systemd --user │
│ macOS → launchd (~/Library/LaunchAgents) │
└─────────────────────────────────────────────────┘
Installation Flow
Follow this checklist in order. Use ask_user for interactive parameter collection.
Phase 1: Environment Detection
- Detect OS:
uname -s→ Linux or Darwin - Detect architecture:
uname -m→ x86_64/amd64 or aarch64/arm64 - Check for existing installation: look for
~/.local/bin/mihomo,~/.config/mihomo/ - If existing installation found, ask user: upgrade, reconfigure, or abort
- Verify
~/.local/binis on PATH; if not, warn user and add to shell profile - Verify user systemd is available (Linux:
systemctl --user statusworks) or launchd (macOS)
What ships with it
4 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.
- yesterday First seen · 242 lines · 65 tokens per session scan D ccfbb37b2530
mihomo-proxy-setup is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,999 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, unrestricted tool access, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.