claude

system2

Multi-agent engineering workflows with spec-driven quality gates, safety hooks, and structured verification.

3 on GitHubby James Nordlundv1.1.1MITupdated 1 month agoworkflow
/

Plugin system2 from marketplace system2-marketplace in DeliberateCode/System2. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (4)

  • compose

    Compose overlay contributions onto the project. Reads overlay manifests, validates, detects conflicts, and materializes a composed CLAUDE.md with overlay-contributed sections. Use when integrating third-party overlays into a System2 project.

  • doctor

    Read-only drift and status check for composed System2 projects. Reports whether base plugin and overlay compositions are current, stale, or broken relative to the lock file.

  • init

    Initialize a project with System2 orchestrator instructions by writing CLAUDE.md to the project root. Use when setting up System2 in a new project.

  • profile

    STRICTLY READ-ONLY listing and inspection of saved overlay profiles. Lists every profile by name, or inspects one profile to show its ordered overlay set with resolved names/versions and stale annotations. Makes no changes to anything: it never composes, never writes project artifacts, and never mut

Subagents (13)

  • code-reviewer

    Performs a senior-level review of the diff against specs for correctness, maintainability, and risk. Use after implementation.

  • design-architect

    Produces spec/design.md with architecture, interfaces, failure modes, and rollout plan. Use after requirements approval.

  • docs-release

    Updates docs, changelog, and release notes. Use near the end of a change set.

  • eval-engineer

    Creates regression evals for agentic or LLM features with goldens and metrics. Use when behavior is non-deterministic.

  • executor

    Implements approved tasks with small diffs and verification. Use after spec/tasks.md is approved.

  • mcp-toolsmith

    Designs MCP tool surfaces with least privilege and safety gates. Use when building or integrating MCP tools.

  • postmortem-scribe

    Writes incident postmortems and captures learnings as guardrails. Use after incidents or major bug escapes.

  • repo-governor

    Establishes repo governance, discovers build/test commands, and documents topology. Use proactively at the start of significant work.

  • requirements-engineer

    Produces and updates spec/requirements.md. In baseline mode, translates approved spec/context.md into EARS requirements with validation and traceability. In corrective mode, analyzes verification failures and distills them into a bounded, high-level corrective requirement delta with explicit regress

  • security-sentinel

    Performs threat modeling and security review, especially for auth, data access, tooling, or agentic features. Use after design and after implementation.

  • spec-coordinator

    Drafts spec/context.md with scope, goals, constraints, and open questions. Use proactively at the start of meaningful work.

  • task-planner

    Converts spec/design.md into spec/tasks.md with atomic tasks and verification steps. Use after design approval.

  • test-engineer

    Runs verification, adds or updates tests, and triages failures. Use after or during implementation.

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain system2?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted