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/gobing-ai/superskill/cc-hooksnpx skills add gobing-ai/superskill --skill cc-hooksgit clone --depth 1 https://github.com/gobing-ai/superskillWrote 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/gobing-ai/superskill/cc-hooks)<a href="https://agentmods.dev/skills/gobing-ai/superskill/cc-hooks"><img src="https://agentmods.dev/badge/skills/gobing-ai/superskill/cc-hooks.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.03613 |
| Opus 5 | $0.00036 | $0.01806 |
| Sonnet 5 | $0.00014 | $0.00723 |
| Haiku 4.5 | $0.00007 | $0.00361 |
Grade A, and why
cc-hooks 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 5d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cc:cc-hooks — Multi-Agent Hook System
Author hooks once in the rulesync-canonical format, deploy to Claude Code, Codex, OpenCode, Pi, and Gemini CLI.
Overview
Hooks execute in response to specific events during a coding agent session. Use this skill when
implementing hooks for security validation, quality enforcement, context loading, or workflow
automation across multiple coding agents: author once in the canonical hooks.json
(HookDefinitionSchema), deploy to 5+ agents.
Canonical Schema (HookDefinitionSchema)
Hooks are authored as a rulesync-canonical hooks.json in the .rulesync/ directory of a plugin. The schema is defined in vendors/rulesync/src/types/hooks.ts:26 as HookDefinitionSchema:
{
"hooks": {
"<HookEvent>": [
{
"type": "command", // "command" | "prompt" | "http"
"command": "superskill hook run <plugin> <hook-id>", // portable PATH command (see below)
"matcher": "Write|Edit", // tool-name regex (control chars stripped)
"timeout": 5000, // ms; optional
"failClosed": true, // optional — block action on hook failure (Cursor)
"loop_limit": 3, // optional — prompt re-injection cap
"name": "write-guard", // optional
"description": "Block dangerous writes" // optional
}
]
}
}
Field semantics:
type:"command"(deterministic, runs anywhere),"prompt"(Claude Code only — natural-language validation),"http"(webhook).command/matcher/prompt:safeString— must not contain\n,\r, or\0(they are embedded in generated code).timeout: milliseconds before the hook is killed.failClosed: whentrue, a hook failure (crash, timeout, invalid JSON) blocks the action instead of allowing it through. DefaultfailOpenwhere unsupported.loop_limit: cap on prompt re-injections;nullmeans unlimited.
HookEvent Taxonomy
Canonical event names are camelCase. Each tool supports a subset — see vendors/rulesync/src/types/hooks.ts:49 for the full HookEvent union.
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.
- agents/openai.yaml 380 B
- examples/load-context.sh 2.0 KB runs code
- examples/validate-bash.sh 1.8 KB runs code
- examples/validate-write.sh 3.1 KB runs code
- metadata.openclaw 286 B
- references/advanced.md 12 KB
- references/cross-platform.md 7.4 KB
- references/migration.md 6.9 KB
- references/patterns.md 9.7 KB
- references/platform-limits.md 7.6 KB
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.
- 5d ago First seen · 278 lines · 71 tokens per session scan A 8135a7b190fc
cc-hooks is a skill published in the GitHub repository gobing-ai/superskill (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 71 tokens to every session and 3,613 once invoked, about $0.0004 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
agtx-review
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.
cmux-architecture
Skill "cmux-architecture" from manaflow-ai/cmux, covering cmux architecture, package architecture, layers, file organization and documentation.
fabric-exec
Troubleshooting and advanced API reference for fabricexec TypeScript programs, dynamic providers, agents, and schema recovery. Routine pi. coding calls are documented by ambient guidance; load this skill only after an argument-shape error or when an advanced surface needs exact contracts.
fabric-fusion
Multi-model deliberation. Two to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Act mode runs 1–4 read-only references, then one actor reconciles and executes. Use when the cost of being wrong justifies…
cmux-browser
End-user browser automation with cmux. Use when you need to open sites, inspect or interact with browser surfaces, wait for page state, and extract data without stealing focus.
cmux-cloud-vm
Route work to cmux Cloud machines (persistent cloud VMs) from the CLI — cmux vm route/run/agent pick a machine for you; vm tree / surface ls show the surface catalog (This Mac and every machine: terminals, VNC screens, browsers) and vm open / surface open put any of them in a pane; plus create, exec, push/pull, ports…