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 majiayu000/spellbook --skill clash-doctorgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/clash-doctor)<a href="https://agentmods.dev/skills/majiayu000/spellbook/clash-doctor"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/clash-doctor/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/majiayu000/spellbook/clash-doctor"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/clash-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.00688 |
| Opus 5.5 | $0.00036 | $0.00275 |
| Sonnet 5.5 | $0.00018 | $0.00138 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
clash-doctor 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clash Verge Diagnostics
Inspect Clash Verge or mihomo, manage profile-specific routing, and diagnose connectivity.
Routing
- Confirm the target profile, constraints, requested access path, and done-when signal.
- Load
references/full-guide.mdfor commands, templates, and diagnosis matrices. - Load
references/local-hub.mdbeforehub,align,roles,clone,setup-ai, orswitch, and whenever the user says a previous sync did not apply. - Keep the change limited to the requested target.
Safety
- Diagnose and align are read-only. Writes require a shown summary and explicit confirmation.
- Edit enhancement overlays or the confirmed local-hub YAML. Do not edit raw subscription dumps.
tun.route-exclude-addressis union-only.DIRECTis not a TUN bypass.- Never invent or print node IPs, credentials, subscription UIDs, or machine hostnames.
- After an overlay or hub-YAML write, quit and reopen Clash Verge.
PUT /configsdoes not re-merge overlays.
Modes
| Argument | Mode |
|---|---|
| empty or a hostname | diagnose |
profiles / list / ls |
list local and remote profiles |
status |
live kernel, TUN, and selected nodes |
hub / roles |
local-hub topology |
align / sync-check |
read-only multi-machine comparison |
switch-check / health |
pre-switch health |
clone / setup-ai / switch |
confirmed profile writes |
rustdesk / bypass |
TUN exclusion for a relay IP |
Resolve the named target before setup-ai. Apply airport-style enhancement overlays only when that target is type: remote; edit the named hub YAML when it is type: local.
Verify
- Parse the target YAML after every write.
- Query mihomo by trying both Unix sockets and then the configured HTTP controller; fall back on request failure, not socket existence alone.
- For routes,
chains[-1]is the matched group andchains[0]is the dialed node. - Report files changed, commands run, evidence, and remaining risk.
References
references/full-guide.md— commands, templates, and diagnosis matrixreferences/local-hub.md— hub ownership, node roles, alignment, and landmines
What ships with it
2 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.
- 1mo ago Changed · +28 lines · +20 tokens per session 65883e5655e7
- 1mo ago First seen · 30 lines · 71 tokens per session scan A 87c3c07447cd
clash-doctor is a skill published in the GitHub repository majiayu000/spellbook (288 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 688 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
cao-session-management
Find available CAO (CLI Agent Orchestrator) agent profiles, and talk to the conductor and worker terminals of a running CAO session, including unblocking a stuck worker. Use when choosing a profile to launch, messaging or unblocking workers, or diagnosing a stuck session. For preflight, launching, session commands…
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
fast-resume
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.
lov-organize-storage
A storage-organization tool for surveying a whole drive or archive and planning a project-based folder layout. It can rename items within the same drive after confirmation, while keeping a mapping, log, and rollback script.
lov-finder-action
A generator for custom right-click actions in macOS Finder, the file manager on Apple computers.