Shared catalog of specialized Crew roles, design/writing crafts, project standards and crew.json. Claude Code commands and Codex skills use the same canonical procedures, with host-specific hook adapters.
★not rated 2
changed 2d agoA
tokens not measured
originalMIT
A bounded autonomous feature-development workflow in which Claude orchestrates implementation and Codex independently enhances, plans, and reviews the work.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Multi-turn planning system for creating high-quality implementation designs. Two AI agents (Architect and Reviewer) collaborate through iterative refinement until consensus.
Pre-mortem coaching for software projects. Runs an imagined-failure facilitation session, then produces a kickoff document with ranked risks, mitigations, and early-warning signals.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Spec-driven development for AI agents. Define what to build, let the agent build it right. Vibeflow separates thinking from coding with specs, guardrails, and audits — grounded in your project's real patterns.
★not rated 2
changed 3d agoA
tokens not measured
copy · 100%MIT
Requirements-driven development for Claude Code. Validate specs and tasks against project requirements, break down features with automatic compliance checking, and ensure every implementation meets organizational standards.
Capability-first AI development skill graph (Anthropic-native): plan → build with a warm-context orchestrator, contract-wired skills, and independent verification.
★not rated 2
changed 6d agoA
tokens not measured
originalMIT
Full agentic layer framework implementing the Codebase Singularity concept - enabling AI agents to operate your codebase autonomously through planning, building, reviewing, and fixing workflows. Implements Class 1-3 with orchestration capabilities.
Only three files. A minimal spec-driven workflow for Claude Code: /tripod:spec interviews you and writes SPEC.md + CLAUDE.md, /tripod:tasks turns them into TASKS.md, /tripod:next executes tasks one by one.
★not rated 2 25d agoA
tokens not measured
originalMIT
AI-powered PRD generator with official-source research validation, self-evolving project skills, CI/CD pipeline generation, and local documentation cache for AI-assisted development.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Fable-style agentic working method for any model — surface the unknowns before building on vague specs or unfamiliar code (blind-spot pass, interview, variants, log assumptions, stay in the loop).
★not rated 2 2mo agoA
tokens not measured
originalMIT
Autonomous dev pipeline generator. /autocode-flow:autocode-new scans & configures, /autocode-flow:autocode auto-executes plan → tdd → code → test → verify with zero human intervention.
★not rated 2 6mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: