# Context Modes

> Structured work modes for agent sessions. Set LACP_CONTEXT_MODE to activate: tdd (red-green-refactor), debugging (4-phase root cause), sprint (pre-agreed criteria), verification (evidence-before-claims), brainstorm (design first), think (pause-and-reflect), orchestrate (task decomposition). Each mode injects behavioral rules at session start.

- Skill: `0xnyk/context-modes` (Agent Skill, multi-file: 12 files)
- Install (CLI): `npx skillmds@latest add 0xnyk/context-modes`
- Raw SKILL.md: https://api.skillmd.com/api/skills/0xnyk/context-modes/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: 0xNyk (https://skillmd.com/u/0xnyk)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/0xnyk/context-modes

---


# Context Modes

Set `LACP_CONTEXT_MODE` environment variable to activate a mode:

| Mode | Purpose |
|------|---------|
| `tdd` | Strict RED-GREEN-REFACTOR — no code without a failing test |
| `debugging` | 4-phase systematic root cause investigation |
| `sprint` | Pre-agreed completion criteria evaluated at stop |
| `verification` | Evidence-before-claims discipline |
| `brainstorm` | Design exploration — no code until design approved |
| `think` | Pause-and-reflect before every action chain |
| `orchestrate` | Decompose into subtasks before executing |
| `implementation` | Focused implementation partner |
| `review` | Code review mode |
| `thinking-partner` | Challenge assumptions, surface blind spots |
| `handoff-resume` | Continue from previous session handoff |

Each mode is a markdown file that gets injected as system context at session start.