playbook
25Command
How to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails.
317 tagged coding agent, measured the same way as everything else here.
Browse within: infrahub 43infrastructure 43ai-coding-agent 29codex-cli 25context-engineering 25design-system 25agent-orchestration 24coding 22pi 20openai 16remote-control 16telegram 16ai-assistant 14hooks 14
Command
How to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails.
Command
Draft a plan and open it in the annotator UI for user review.
Command
Show test-plugin status.
Command Claude Code
This document describes the standard release process for agtrace.
Command
Advanced history search and analysis for AI coding agent sessions.
Command
Inspect and query historical AI coding agent sessions.
raphaeltm/simple-agent-manager
Command Claude Code
End-to-end task execution — research, plan, implement, review, and merge via PR.
raphaeltm/simple-agent-manager
Command Claude Code
Generate a custom checklist for the current feature based on user requirements.
raphaeltm/simple-agent-manager
Command Claude Code
Create or update the feature specification from a natural language feature description.
Command Claude Code
Implement tasks from an OpenSpec change (Experimental).
Command Claude Code
Propose a new change - create it and generate all artifacts in one step.
Command Claude Code
Update a change - revise existing planning artifacts and keep them coherent (Experimental).
Command
Explicitly turn the task-local Grok executor mode on or off.
Command
Discover, verify, and persist the local HTTP proxy used by Grok Build Supervisor.
gvkhosla/compound-engineering-pi
Command
Quiz me using the coding-tutor skill.
gvkhosla/compound-engineering-pi
Command
Commit and push your tutorials to the GitHub repository for backup and mobile reading.
gvkhosla/compound-engineering-pi
Command
Teach me something using the coding-tutor skill.
Command
Run a Pi review that challenges the implementation approach and design choices.
Command
Delegate multiple independent tasks to Pi for parallel execution via pi-subagents.
Command
Run a Pi code review against local git state.
Command
.opensunstar/wiki/candidates/rd-backfill-auto- / ├── candidate.json # engine: "rd-backfill-auto", sourcecommit, createdat └── wiki/ ├── index.md └── runbooks/ .md # wiki schema frontmatter.
Command
A command that turns reusable lessons from a completed change into proposed entries for a project knowledge base, a collection of shared technical and business notes.
Command
A command that scans selected source-code paths for business anchors such as message topics, status values, identity constants, interface names, and table names. It saves these findings as candidates for human review.
Command
Multi-agent code review with confidence scoring.