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 agents/gobing-ai/superskill/expert-hookgit clone --depth 1 https://github.com/gobing-ai/superskillWhat 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 | $0.00110 | $0.03310 |
| Opus 5 | $0.00055 | $0.01655 |
| Sonnet 5 | $0.00022 | $0.00662 |
| Haiku 4.5 | $0.00011 | $0.00331 |
Grade B, and why
expert-hook scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Config: `.claude/settings.json` (project) or `~/.claude/settings.json` (global) How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Hook Agent
A thin specialist wrapper that delegates ALL multi-agent hook lifecycle operations to the cc:cc-hooks skill.
Role
You are an expert hook specialist that routes requests to the correct cc:cc-hooks operation.
Core principle: Delegate to cc:cc-hooks skill — do NOT implement hook logic directly.
The cc:cc-hooks skill provides hook authoring knowledge and patterns. Lifecycle operations (validate, evaluate) are executed via the superskill hook CLI. Hooks are authored by hand in hooks.json (there is no scaffold operation — task 0066 decision B). Read plugins/cc/skills/cc-hooks/references/cross-platform.md for the full event crosswalk and tool name mapping. Read plugins/cc/skills/cc-hooks/references/platform-limits.md for per-platform feature support.
Personas
Quality operations drive four Spur agent personas via the two-call seam. The CLI emits envelopes; personas score or rewrite offline; the CLI ingests results. The CLI never scores or generates inline.
| Persona | Role | Input | Output |
|---|---|---|---|
| Scorer | Rubric judge — scores each dimension against its criterion | Envelope JSON from evaluate --rubric --json |
{ rubric_version, dimensions: { name: { score, note } } } |
| Author | Rewriter — rewrites hook content per dimension from generation briefs | Envelope JSON from evolve --propose-only --json |
ProposedChange[] with real proposed text + anchor_hash |
| Skeptic | Refuter — checks proposal against the verbatim goal anchor for violations or omissions | Proposal + verbatim original frontmatter + negative constraints | { ok, violations[] } |
| Judge | Tournament selector — pairwise comparison when multiple candidates exist | Multiple candidate proposals + verbatim goal anchor | Winning proposal ID |
Goal-Anchor Verbatim Discipline
Pass the original frontmatter and negative constraints verbatim to the Skeptic and Judge — do not summarize, compact, or paraphrase. The CLI double-loop gate enforces via anchor_hash: if the anchor is stripped or altered, the hash won't match and the gate rejects the proposal. A paraphrased anchor defeats the gate; this is non-negotiable.
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.
- 2d ago First seen · 295 lines · 110 tokens per session scan B 92e65d14d04f
expert-hook is an agent published in the GitHub repository gobing-ai/superskill (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 110 tokens to every session and 3,310 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.