Add community skills, agents, system prompts from 22+ sources
Community Skills (32): - jat: jat-start, jat-verify, jat-complete - pi-mono: codex-cli, codex-5.3-prompting, interactive-shell - picoclaw: github, weather, tmux, summarize, skill-creator - dyad: 18 skills (swarm-to-plan, multi-pr-review, fix-issue, lint, etc.) - dexter: dcf valuation skill Agents (23): - pi-mono subagents: scout, planner, reviewer, worker - toad: 19 agent configs (Claude, Codex, Gemini, Copilot, OpenCode, etc.) System Prompts (91): - Anthropic: 15 Claude prompts (opus-4.6, code, cowork, etc.) - OpenAI: 49 GPT prompts (gpt-5 series, o3, o4-mini, tools) - Google: 13 Gemini prompts (2.5-pro, 3-pro, workspace, cli) - xAI: 5 Grok prompts - Other: 9 misc prompts (Notion, Raycast, Warp, Kagi, etc.) Hooks (9): - JAT hooks for session management, signal tracking, activity logging Prompts (6): - pi-mono templates for PR review, issue analysis, changelog audit Sources analyzed: jat, ralph-desktop, toad, pi-mono, cmux, pi-interactive-shell, craft-agents-oss, dexter, picoclaw, dyad, system_prompts_leaks, Prometheus, zed, clawdbot, OS-Copilot, and more
This commit is contained in:
41
hooks/community/jat/post-bash-agent-state-refresh.sh
Executable file
41
hooks/community/jat/post-bash-agent-state-refresh.sh
Executable file
@@ -0,0 +1,41 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# Post-Bash Hook: Agent State Refresh
|
||||
#
|
||||
# Detects when agent coordination commands are executed and triggers
|
||||
# statusline refresh by outputting a message (which becomes a conversation
|
||||
# message, which triggers statusline update).
|
||||
#
|
||||
# Monitored commands:
|
||||
# - am-* (Agent Mail: reserve, release, send, reply, ack, etc.)
|
||||
# - jt (JAT Tasks: create, update, close, etc.)
|
||||
# - /jat:* slash commands (via SlashCommand tool)
|
||||
#
|
||||
# Hook input (stdin): JSON with tool name, input, and output
|
||||
# Hook output (stdout): Message to display (triggers statusline refresh)
|
||||
|
||||
# Read JSON input from stdin
|
||||
input_json=$(cat)
|
||||
|
||||
# Extract the bash command that was executed
|
||||
command=$(echo "$input_json" | jq -r '.tool_input.command // empty')
|
||||
|
||||
# Check if command is empty or null
|
||||
if [[ -z "$command" || "$command" == "null" ]]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Detect agent coordination commands
|
||||
# Pattern: am-* (Agent Mail tools) or jt followed by space (JAT Tasks commands)
|
||||
if echo "$command" | grep -qE '^(am-|jt\s)'; then
|
||||
# Extract the base command for display (first word)
|
||||
base_cmd=$(echo "$command" | awk '{print $1}')
|
||||
|
||||
# Output a brief message - this triggers statusline refresh!
|
||||
# Keep it minimal to avoid cluttering the conversation
|
||||
echo "✓ $base_cmd executed"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# No agent coordination command detected - stay silent
|
||||
exit 0
|
||||
Reference in New Issue
Block a user