hooks agents

rennf93/opus-fable-playbook

Command

Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.

rennf93/opus-fable-playbook

Command

Report fable-mode posture — output style, model/effort, hook telemetry drift counts.

rennf93/opus-fable-playbook

Hook

Runs when you submit a prompt, before the agent sees it, executing prompt-nudge.sh. From rennf93/opus-fable-playbook.

rennf93/opus-fable-playbook

Hook

Runs when a subagent finishes, executing stop-gate.sh. From rennf93/opus-fable-playbook.

rennf93/opus-fable-playbook

Hook

Runs before the agent uses a tool for Bash tool calls, executing bash-discipline.sh. From rennf93/opus-fable-playbook.

rennf93/opus-fable-playbook

Skill Claude CodeCodex

Use when a task involves 2+ independent units of work (files, modules, questions) or any broad codebase sweep — enforces Fable's delegation-first parallel orchestration.

rennf93/opus-fable-playbook

Skill Claude CodeCodex

Use before ending any turn that involved multi-step work — Fable's end-of-turn gate catches promised-but-undone work, buried findings, and unverified claims.

rennf93/opus-fable-playbook

Skill Claude CodeCodex

Use when about to write your final reply, a summary, PR description, commit message, or any user-facing conclusion — enforces Fable's outcome-first, prose-first communication contract.

ryo-ebata/cc-audit

Command Claude Code

Run just ci-all and fix all errors that occur.

ryo-ebata/cc-audit

Skill Claude CodeCodex

CLI tool design and architecture best practices inspired by Biome, OxcLint, and other modern Rust tools. Use when designing new features, refactoring architecture, or reviewing structural decisions.

ryo-ebata/cc-audit

Skill Claude CodeCodex

Rust coding best practices for cc-audit development. Use when writing new Rust code, reviewing code, or refactoring. Covers error handling, safety, performance, and idiomatic patterns.

ryo-ebata/cc-audit

Skill Claude CodeCodex

Guide development using Kent Beck's TDD methodology. Use when implementing new features, fixing bugs, or adding rules to cc-audit. Enforces test-first approach with Red-Green-Refactor cycle.

ryo-ebata/cc-audit

MCP server Claude CodeCodexCursor +2

MCP server "cc-audit" as configured in ryo-ebata/cc-audit. Launched with ./target/release/cc-audit serve.

ryo-ebata/cc-audit

Command Claude Code

Command "dangerous-deploy" from ryo-ebata/cc-audit, covering deploy command, steps, build, deploy with elevated privileges and sync secrets to remote.

ryo-ebata/cc-audit

Command Claude Code

Build the application for development or production.

ryo-ebata/cc-audit

Agent Claude Code

An agent with security issues for testing.

ryo-ebata/cc-audit

Agent Claude Code

A safe agent with minimal permissions.

realgarit/fable-baton

Plugin Claude Code

Turns Fable 5 into a token-frugal orchestrator: Fable keeps judgment, tiered Opus/Sonnet/Haiku agents do the labor.

realgarit/fable-baton

Instructions file CodexOpenCode

Instructions for realgarit/fable-baton, covering fable-baton: agent instructions, project memory (distilled), cross-agent conventions and working notes.

realgarit/fable-baton

Instructions file

Instructions for realgarit/fable-baton, a project described as: Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents.

realgarit/fable-baton

Agent

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

realgarit/fable-baton

Agent

Standard engineering execution. Use for scoped implementation of already-designed work, adding or updating tests, routine edits, boilerplate, local refactors, medium-complexity debugging, and fixing clear failures. Does not make product calls or change architecture.

realgarit/fable-baton

Agent

Cheap evidence gathering. Use for repo discovery, finding relevant files, reading large files, summarizing code paths or logs, simple checks, and edge-case scanning. Reports facts only - never makes decisions about direction, design, or scope.

realgarit/fable-baton

Hook

Runs when a session starts, executing session-start.sh. From realgarit/fable-baton.