/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
$ npx -y skills add 0xNyk/lacp --skill context-modes --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/context-modes
Context preview
The summary Claude sees to decide when to auto-load this skill.
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
SKILL.md
context-modes.SKILL.mdname: context-modes description: "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."
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.
Local policy, evidence, and recovery controls for coding agents. LACP wraps Claude, Codex, Hermes, and other CLI agents with deterministic routing, approval gates, execution records, memory controls, and rollback paths.
Repo: 0xNyk/lacp
Other skills on lacp.
- /quality-gate
Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for
Open skill - /session-hardening
Production hardening for agent sessions. Includes pretool guards (blocks rm -rf, co-author injection, publishing without approval, data exfiltration), continuous QA (runs tests every N file writes), and session context injection (git state, focus brief, handoff artifacts).
Open skill