// Research a library and create comprehensive documentation in .claude/docs/libraries/.
Add a feature to an existing codebase with Codex-first multi-agent collaboration (Codex + Opus 4.6). Codex CLI is consulted in EVERY phase for scope analysis, architecture design, and implementation planning. Phase 1: Scope & impact analysis (Opus subagent codebase scan + Codex scope analysis + Claude user clarification). Phase 2: Design & plan (Codex architecture design + Codex implementation plan + Codex validation). Phase 3: Implementation routing by complexity (SIMPLE: Codex direct, MODERATE: Codex + /team-review, COMPLEX: /team-implement).
Comprehensive onboarding for new or returning contributors. Scans repository artifacts (git history, CLAUDE.md / AGENTS.md, project rules, skill catalog, DESIGN.md, research & library notes, checkpoints, agent-team logs) and synthesizes a GUIDE.md at the repository root summarizing what has been worked on, why, and how to resume work.
Save full session context: git history, CLI consultations, Agent Teams activity, and discover reusable skill patterns — all in one run. No flags needed. Run at session end, after major milestones, or when you want to capture learnings.
Codex CLI handles planning, design, and complex code implementation. Use for: architecture design, implementation planning, complex algorithms, debugging (root cause analysis), trade-off evaluation, code review. External research is NOT Codex's job — use general-purpose subagent (Opus) instead. Explicit triggers: "plan", "design", "architecture", "think deeper", "analyze", "debug", "complex", "optimize".
Analyze project structure and populate the "Repository Identity" section of CLAUDE.md (Zone B) plus AGENTS.md.
Time-boxed technical investigation/feasibility study with Codex-first multi-agent collaboration (Codex + Opus 4.6 + Agent Teams). Codex CLI is consulted in EVERY phase for question framing, feasibility analysis, and final evaluation. Phase 1: Frame the investigation question & constraints (Claude user interaction + Codex question decomposition). Phase 2: Parallel investigation (Agent Teams: Researcher [Opus external research] + Feasibility Analyst [Codex deep analysis] + optional prototype). Phase 3: Codex synthesis into go/no-go recommendation & research report. Produces a DECISION DOCUMENT, NOT an implementation plan. Use /add-feature or /start-feature after a GO decision.
| name | research-lib |
| description | Research a library and create comprehensive documentation in .claude/docs/libraries/. |
| disable-model-invocation | true |
Research $ARGUMENTS and create documentation in .claude/docs/libraries/.
Use a general-purpose subagent (Opus) with WebSearch/WebFetch for comprehensive library research:
Agent tool:
subagent_type: "general-purpose"
prompt: |
Research: {library}. Find latest version, official documentation,
key features, constraints, best practices, known issues, and usage patterns.
Use WebSearch and WebFetch to gather information.
Save results to .claude/docs/libraries/{library}.md
Return concise summary.
If the subagent is unavailable, verify via manual web search:
Basic Information
Core Features
Constraints & Notes
Usage Patterns in This Project
Troubleshooting
.claude/docs/libraries/$ARGUMENTS.md
# {Library Name}
## Overview
- **Version**: {version}
- **License**: {license}
- **Official URL**: {url}
- **Installation**: `{install command}`
## Core Features
{Description of main features}
## Basic Usage
```python
{Code example}
{Good pattern}
{Anti-pattern}
Cause: {cause} Solution: {solution}