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.

Jump to install Review files

Repository: 0xNyk/lacp
Last source activity: April 9, 2026 at 15:16
Detected SKILL.md language: English
Stars: 306
Forks: 2

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/0xNyk/lacp/tree/main/plugin/skills/context-modes.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/0xNyk/lacp --skill context-modes

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

12 files

SKILL.md

Source instructions · Read-only preview

name: 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.

View on GitHub

Back to search Back to installation

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 session continuity. Use sprint contracts to define done-criteria before building.

2026-04-09

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). Activates automatically via hooks.

2026-04-09

View all from this repository

context-modes

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository