Stats
Actions
Available In
Tags
Plugin
context-engine
Agentic orchestration framework for Claude Code. Agent Teams, subagents, progressive-disclosure skills, hooks, checkpoints, knowledge layer, and metrics.
What's Inside
Slash Commands21
/adapt - Adapt Project to Plugin Standards
/adapt
Audit the project against the plugin's prescribed standards and refactor the project to conform. Run after `/init` to identify gaps, then apply fixes per dimension.
/cancel - Cancel an In-Progress or Approved Feature
/cancel
Mark a feature as CANCELLED, capture learnings from partial work, and optionally clean up branches and checkpoints.
/checkpoint - Checkpoint Management
/checkpoint
Create, list, rollback, and clean hybrid checkpoints (git tag + .context/ snapshot).
/create-skill - Create a New Skill
/create-skill
Create a new skill with proper structure, scoped content, and a quality review pass. Adds the skill to the framework's skill table and updates the skill profile.
/debug - Diagnose and Fix a Bug
/debug
Something is broken. Uses parallel hypothesis testing via Agent Team for complex bugs, or single `debugger` subagent for simple ones.
Agents6
debugger
/debugger
Systematically diagnoses and resolves bugs. Uses diagnostic reasoning, log analysis, hypothesis testing, and bisection. Use when something is broken and needs investigation.
implementer
/implementer
Executes PRP steps following the project's testing strategy. Works sequentially, validates after each step.
mcp-researcher
/mcp-researcher
Executes MCP tool operations in isolated context and returns compressed summaries. Use for browser automation, database queries, documentation lookups, and other MCP-heavy tasks.
planner
/planner
Creates structured PRPs (Product Requirements Prompts) from research notes. Produces actionable plans with file paths, test coverage needs, and validation criteria.
researcher
/researcher
Explores codebase structure, finds relevant files, and returns distilled summaries. Use before planning to understand existing code without consuming main context.
Skills23
api-conventions
/api-conventions
API conventions for this project. Auto-loaded when working with routes, controllers, and endpoint files to ensure consistent API patterns.
auth-security
/auth-security
Authentication and security patterns - JWT, OAuth, sessions, RBAC, input validation. Auto-loaded when working with auth, middleware, or security files.
chrome-devtools
/chrome-devtools
Chrome DevTools debugging and browser automation via MCP. Auto-loaded when working with browser debugging, performance analysis, or web inspection tasks.
context-system
/context-system
Context Engine framework reference. Auto-loaded when working with .context/, agents, commands, or hooks. Supplements CLAUDE.md with role and skill details.
context7-docs
/context7-docs
Library documentation lookup via Context7 MCP. Use when you need current docs for any library, framework, or API. Prevents hallucinated APIs by fetching real documentation.
MCP Servers1
Stats
Version0.2.1
Released
LanguageShell
Stars1
MaintenanceExcellent
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Caution
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
