SubagentStop
49Hook
Runs when a subagent finishes, executing subagent-tracker.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
copy · 91% MIT
Hook
Runs when a task is marked completed, executing step-completed.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
original MIT
SessionEnd
51Hook
Runs when a session ends, executing session-end.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
original MIT
Stop
52Hook
Runs when the agent finishes a response, executing goal-completion.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
original MIT
StopFailure
53Hook
Runs on the StopFailure event, executing stopfailure-logger.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
original MIT
PreCompact
54Hook
Runs before the context is compacted, executing pre-compact.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
original MIT
ConfigChange
55Hook
Runs on the ConfigChange event, executing config-change-guard.sh via bash. From martineserios/thebrana.
3 2d ago A
tokens not measured
original MIT
Skill Claude CodeCodex
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
3 2d ago E 45 tokens
original MIT
caveman
57Skill Claude CodeCodex
Ultra-compressed mode — 65-75% fewer tokens, preserving technical accuracy. Strips filler, hedging, pleasantries. Code/commits stay in normal language.
3 2d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Cloud Run expert guidance. Use when deploying services, running jobs, or managing worker pools for HTTP, scheduled tasks, or background processing.
3 2d ago A 32 tokens
original MIT
Skill Claude CodeCodex
Design event-driven systems: contracts, topics, consumers, retries, idempotency, and sagas. Use for asynchronous workflows, reliability patterns, retry/replay design, DLQ handling. NOT for CRUD APIs or ETL pipelines.
3 2d ago A 52 tokens
original MIT
fastapi
60Skill Claude CodeCodex
FastAPI best practices + Pydantic. Use when building or reviewing FastAPI APIs.
3 2d ago A 21 tokens
original MIT
Skill Claude CodeCodex
Production-ready Cloud Run on GCP: containerized services, Cloud Run Functions, cold start optimization, Pub/Sub integration, Cloud SQL, Secret Manager, concurrency tuning. Covers sharp edges and gotchas.
3 2d ago D 45 tokens
original MIT
Skill Claude CodeCodex
LLM evaluation — automated metrics, human feedback, benchmarking. Use when testing performance, measuring AI quality, or establishing evaluation frameworks.
3 2d ago A 31 tokens
original MIT
Skill Claude CodeCodex
Next.js App Router — Server Components, Actions, streaming, caching. Use when building or migrating Next.js apps.
3 2d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Postgres optimization — 70 rules (queries, indexes, RLS, concurrency). Use when writing SQL or reviewing schema.
3 2d ago A 30 tokens
copy · 75% MIT
Skill Claude CodeCodex
Core Supabase — DB, Auth, Realtime, Storage, RLS, Edge Functions. Triggers on ANY Supabase task.
3 2d ago A 32 tokens
copy · 86% MIT
supabase
66Skill Claude CodeCodex
Use when doing ANY task involving Supabase: Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues, supabase-js, @supabase/ssr, RLS, schema migrations, CLI, MCP server. Includes security checklist.
3 2d ago A 58 tokens
original MIT
vercel-react
67Skill Claude CodeCodex
React/Next.js performance — 70 rules (waterfalls, bundle, re-renders). Use when reviewing or writing React/Next.js code.
3 2d ago A 34 tokens
copy · 89% MIT
vitest
68Skill Claude CodeCodex
Vitest unit testing — Vite-powered, Jest-compatible. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.
3 2d ago A 33 tokens
original MIT
web-design
69Skill Claude CodeCodex
UI review against Web Interface Guidelines. Use when asked to review UI, check accessibility, or audit design.
3 2d ago A 24 tokens
original MIT
Skill Claude CodeCodex
Best practices for webhook handlers: verify → parse → handle idempotently. Covers idempotency, error handling, retry logic, framework-specific gotchas (Express, Next.js, FastAPI). Use when implementing any webhook receiver.
3 2d ago A 52 tokens
original MIT
align
71Skill Claude CodeCodex
Align a project to brana practices — assess gaps, plan, implement, verify. Auto-detects type. Use when setting up a new project or realigning an existing one.
3 2d ago B 39 tokens
original MIT
backlog
72Skill Claude CodeCodex
Manage the backlog — plan, track, navigate phases and epics. Use when planning phases, viewing roadmaps, or restructuring work.
3 2d ago A 30 tokens
original MIT