haku
claudeLean leadership plugin that runs the decide → spec → evidence loop — 8-skill core + 5 gate agents, with 8 opt-in role packs (product, people, engineering)
52 skills · 5 agents · hooks
Safety-proportional process for agentic SDLC: trivial changes skip ceremony, risky changes earn it. Risk-tiered loop with fail-twice auto-promotion and a verify-before-done hard gate.
Plugin tempo from marketplace vibekit in shrwnsan/vibekit-claude-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
risk-triageClassify a coding task as risk tier 0, 1, or 2 before starting work, and route to the matching tier flow. Use at the start of any non-trivial task, whenever a task's risk is unclear, or after a second failed attempt on the same fix. Part of the tempo plugin.
tier-0-trivialTier-0 trivial-change rules (typo, copy tweak, one-line fix, docs update). Rarely needs loading — the rules below are the whole flow; consult only when unsure a change qualifies as trivial.
tier-1-standardTier-1 standard-change flow — one-line plan note, test-first, single agent, systematic debugging on failures. Use for normal feature work and bug fixes with clear requirements. Promote to the tier-2-risky flow if the same fix fails twice. Part of the tempo plugin.
tier-2-riskyTier-2 risky-change flow — short plan file, deliberate build, review gate and verify gate before done. Use for architectural changes, concurrency and rate-limiting work, public API changes, ambiguous requirements, security/auth/data work, or after a tier-1 task failed twice. Part of the tempo plugin
"${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"
Lean leadership plugin that runs the decide → spec → evidence loop — 8-skill core + 5 gate agents, with 8 opt-in role packs (product, people, engineering)
52 skills · 5 agents · hooks
Essential Claude Code workflow and context engineering tools for productive development
4 skills · 2 commands · 1 agent · hooks
Enhanced web search with multi-service fallback (TinyFish, Tavily, Brave, Exa, Jina, plus keyless Firecrawl/Defuddle) — works without API keys
1 skill · 1 agent · hooks
Sound notifications and alerts for Claude Code tasks
hooks
Pre-classifier permission gate for auto mode: System One decision models (TypeSafe Jev, Liquid d1, compatible endpoints) as typed allow/ask/deny PreToolUse decisions. Fails safe — errors hand back to Claude Code's own classifier.
hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.