caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Claude Code hooks that inject feedback rules, enforce them on tool calls and at stop time, and run per-project quality gates defined in .claude/gate.yaml
Plugin feedback-gate from marketplace claude-hook-gate in nonchan7720/claude-hook-gate. Commands read from the repo's manifest — 2 days ago.
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.
effort-highSwitch the reasoning effort of the rest of the current turn to high. Invoke it when a feedback-gate hook message (for example the stop_review of gate.yaml at Stop / SubagentStop) tells you to, or when the user asks to run a task at high effort. It only changes the effort; it gives no task of its own
effort-lowSwitch the reasoning effort of the rest of the current turn to low. Invoke it when a feedback-gate hook message (for example the stop_review of gate.yaml at Stop / SubagentStop) tells you to, or when the user asks to run a task at low effort. It only changes the effort; it gives no task of its own.
effort-maxSwitch the reasoning effort of the rest of the current turn to max. Invoke it when a feedback-gate hook message (for example the stop_review of gate.yaml at Stop / SubagentStop) tells you to, or when the user asks to run a task at max effort. It only changes the effort; it gives no task of its own.
effort-mediumSwitch the reasoning effort of the rest of the current turn to medium. Invoke it when a feedback-gate hook message (for example the stop_review of gate.yaml at Stop / SubagentStop) tells you to, or when the user asks to run a task at medium effort. It only changes the effort; it gives no task of its
effort-xhighSwitch the reasoning effort of the rest of the current turn to xhigh. Invoke it when a feedback-gate hook message (for example the stop_review of gate.yaml at Stop / SubagentStop) tells you to, or when the user asks to run a task at xhigh effort. It only changes the effort; it gives no task of its o
feedbackCreate, update and review (periodic inventory) the feedback rule files that feedback-gate reads, `~/.claude/feedback/*.md` (global) and `<project>/.claude/feedback/*.md` (project). Use when the user gives feedback, a correction or a preference worth remembering, asks to save or record a rule, raise
gateCreate, update or review a project's `.claude/gate.yaml`, the per-project quality gate of feedback-gate (lint, format check, typecheck, tests, build) that runs after Claude edits files and before it stops. Discovers the project's languages, package manager, task runner (Makefile, package.json script
hook-listShow, in the browser, which hooks feedback-gate runs in this project and when - the `.claude/gate.yaml` rules / consistency_checks / session_start with their commands, and the feedback rules with how they are injected and each `enforce` entry (event, severity, condition, check command), plus the ina
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" SessionStart
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" UserPromptSubmit
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" PostToolUse
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" Notification
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" Stop
bash "${CLAUDE_PLUGIN_ROOT}/scripts/hook.sh" SubagentStop
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.