claude-code-hooks hooks

sheeki03/Few-Word

Hook

Runs when a session ends, executing archive_plan.py. From sheeki03/Few-Word.

sheeki03/Few-Word

Skill Claude CodeCodex

Use this skill when tool outputs exceed 2000 tokens, tasks span multiple conversation turns, sub-agents need to share state, context window is bloating, plans need to persist across summarization, terminal/log output needs selective querying, or when user mentions "offload context", "dynamic context discovery"…

ViryaZheng/promptly-prompt

Plugin Claude Code

Clarity gate for prompts: intercepts unclear requests and forces AI to restate intent to align with the user, then diagnose the root cause and reuse the domain's mature, established practices before proceeding.

ViryaZheng/promptly-prompt

Hook

Runs when you submit a prompt, before the agent sees it, executing intercept.py via python3. From ViryaZheng/promptly-prompt.

ViryaZheng/promptly-prompt

Skill Claude CodeCodex

Clarity gate for prompts: intercepts unclear requests and forces the model to restate the user's intent to align before working, then diagnose the root cause and reuse the domain's mature, established practices before improvising. Clear prompts pass through untouched.

connerohnesorge/conclaude

Agent Claude Code

Use this agent when you need comprehensive visual testing of user flows, end-to-end testing with browser automation, or validation of UI components and interactions. Note that this agent cannot make any edits or see the filesystem! Examples: - Context: User has implemented a new authentication flow and wants to ensure…

connerohnesorge/conclaude

Agent Claude Code

Emergency escalation agent that ALWAYS gets human input when ANY problem occurs. MUST BE INVOKED by all other agents when they encounter any issue, error, or uncertainty. This agent is HARDWIRED into the system - NO FALLBACKS ALLOWED.

connerohnesorge/conclaude

Agent Claude Code

Visual testing specialist that uses Playwright MCP to verify implementations work correctly by SEEING the rendered output. Use immediately after the coder agent completes an implementation.

connerohnesorge/conclaude

Command Claude Code

Archive a deployed Spectr change and update specs.

connerohnesorge/conclaude

Command Claude Code

only when it is requested or clearly required.

connerohnesorge/conclaude

Command Claude Code

Detect spec drift from code and update specs interactively.

connerohnesorge/conclaude

Hook Claude Code

Runs when a subagent finishes, running conclaude Hooks SubagentStop. From connerohnesorge/conclaude.

connerohnesorge/conclaude

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, running conclaude Hooks UserPromptSubmit. From connerohnesorge/conclaude.

connerohnesorge/conclaude

Hook Claude Code

Runs when the agent asks permission for an action, running conclaude Hooks PermissionRequest. From connerohnesorge/conclaude.

connerohnesorge/conclaude

Settings file Claude Code

Agent settings declaring 11 hook events (SubagentStop, Notification, SubagentStart, PostToolUse) and 0 allowed tools.

connerohnesorge/conclaude

Skill Claude CodeCodex

Generate configuration reference documentation from conclaude-schema.json using src/bin/generate-docs.rs. USE WHEN the schema file changes, configuration options are added/modified, or documentation needs to be regenerated for the website.

connerohnesorge/conclaude

Skill Claude CodeCodex

Generate the conclaude-schema.json configuration schema file using src/bin/generate-schema.rs. USE WHEN the configuration format changes, new config fields are added, or the schema needs to be updated for release or testing.

connerohnesorge/conclaude

Skill Claude CodeCodex

Validate Spectr specifications and change proposals without requiring the spectr binary USE WHEN you're in a sandboxed or restricted execution context and spectr is not available in your path. DO NOT USE WHEN you need a lightweight alternative for task acceptance, but have the spectr binary available. DO NOT USE when…

connerohnesorge/conclaude

Instructions file

Claude Code instructions for connerohnesorge/conclaude, covering you are the orchestrator, your role: master orchestrator, your mandatory workflow, step 1: analyze & plan (you do this) and step 2: delegate to subagents (one todo at a time).

zxkane/autonomous-dev-team

Hook Claude Code

Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing block-push-to-main.sh, block-commit-outside-worktree.sh, check-design-canvas.sh, check-code-simplifier.sh, check-shellcheck.sh, check-pr-review.sh, check-unit-tests.sh, warn-skip-verification.sh, check-rebase-before-push.sh and…

zxkane/autonomous-dev-team

Hook Claude Code

Runs after a tool call finishes for Bash tool calls, executing post-git-action-clear.sh and post-git-push.sh (4 commands). From zxkane/autonomous-dev-team.

zxkane/autonomous-dev-team

Hook Claude Code

Runs when the agent finishes a response, executing verify-completion.sh. From zxkane/autonomous-dev-team.

zxkane/autonomous-dev-team

Settings file Claude Code

Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).

zxkane/autonomous-dev-team

Instructions file CodexOpenCode

AGENTS.md instructions for zxkane/autonomous-dev-team, covering autonomous dev team, install skills, available skills, autonomous-dev and autonomous-review.