209 tagged hooks, measured the same way as everything else here.
Browse within: ai-workflow 38Guardrails 18code-quality 14claude-code-plugins 11plugin-system 11harness 10harness-engineering 10quality-enforcement 10MLOps 9cicd 9ml 9Orchestration 8markdown 8ai-coding-agent 7
Agent
Dedicated adjacent-risk sweep of a changed area — the structural substitute for "Fable-style noticing" on Opus/Sonnet. Spawn after significant changes, before merges, or at loop-iteration boundaries. Read-only; returns ranked load-bearing observations, not a lint report. Still valuable on Opus 5 as a dedicated…
Agent
Plays "what could go wrong" against a Wave's diff. Surfaces race conditions, edge cases, silent failures, and operability gaps that other reviewers miss. Triggered LAST in the review pipeline (after spec-compliance and security have completed) so it can avoid duplicating their findings.
Agent
Re-validates a single finding produced by another reviewer with fresh context. Returns valid / invalid / unsure. Triggered by /mumei:compose after the 3 reviewers complete (spec-compliance / security / adversarial) — invoked once per finding in parallel for severity=HIGH/CRITICAL findings. Filters false positives…
Agent
Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…
Agent
Over-engineering hunter. Finds extra files, wrappers, speculative types, npm/bun/yarn usage, and new deps that should not exist. Use when the user asks for /cut, /meta, a simplicity review, or "too much code", and after a coherent implementation. Do not use for comment-only review (Comment Sicko).
Agent
Bugbot-class logic-bug and vulnerability hunter for the current diff. Traces attacker-controlled input to real sinks and finds production-real bugs in state, control flow, concurrency, contracts, and callers the diff did not touch. Use when the user asks for /hunter, /meta, a bug hunt, a security pass, or a review of…
Agent
Skeptical verifier. Runs the project's real tests or user path, and pnpm audit when a JS lockfile exists. Reports proven vs claimed. Use when the user asks for /prove, /meta all, or says the work is done. Do not trust the parent summary. Do not edit code or weaken tests. Never npm or bun.
Agent
Diğer ajanların çıktısını bağımsız olarak denetler. Mantık hatası, tutarsızlık, doğrulanmamış varsayım arar. Kod yazmaz, sadece değerlendirir.
Agent
Veritabanı görevlerini üstlenir. Şema tasarımı, migration, sorgu yazımı/optimizasyonu, indeksleme, veri bütünlüğü.
Agent
LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.
Agent
You are an independent design reviewer. Review BRAINSTORM.md to find issues that main agent and user may have overlooked during discussion.
Agent
You are an independent challenger for task decomposition. Your goal is to find problems in task breakdown.
Agent
The current test execution owner is the dow test CLI. The /test workflow entry invokes that CLI; it does not dispatch a second independent test plan.
Agent Claude Code
Database operations specialist for SQLite and Entity Framework Core. Use for schema design, migrations, seed data, query optimization, and database troubleshooting.
Agent Claude Code
Expert .NET code reviewer. Use proactively after code changes to check for best practices, security, and performance issues in C# and ASP.NET Core code.
Agent Claude Code
Security-focused code reviewer. Use proactively to scan for vulnerabilities, secret leaks, SQL injection, XSS, CSRF issues, and authentication/authorization problems.
Agent
System-design specialist. Use PROACTIVELY for architectural decisions, new subsystems, interface/data-model design, or significant refactors. Produces a design note / ADR with trade-offs. Read-only — designs, does not implement.
Agent
Expert code-review specialist. MUST BE USED immediately after writing or modifying code, before merge. Reviews quality, correctness, and maintainability. Read-only — reports findings with severity, does not edit.
Agent
Long-running-agent operator. Use to drive ONE iteration of an unattended /operate run — advance the task by a single increment, then checkpoint. Enforces the guardrails via step.js and never continues past a halt. Honors the git boundary. May edit code.
Agent
Classify a user rule into scope and enforcement mechanism. Use when analyzing a rule from /remember that has no explicit scope flag.
Agent
An agent that maps a code patch: which parts changed, what each change is meant to do, and how the changed parts depend on one another.
Agent
An agent that explains how a code change alters what a program does while it runs, including how data moves through the code before and after the change.
Agent
A Python code teacher that explains only unfamiliar Python syntax and patterns appearing in changed code. It focuses on why each construct was used there, rather than giving a general lesson.