362 tagged OpenSpec, measured the same way as everything else here.
Browse within: workflow 29ai-workflow 26multi-agents 22ai-tooling 19harness 19context-engineering 12experimental 12[openspec, archive] 11[openspec, change] 11architectural-decision-records 9c4model 9claude-code-plugins-marketplace 9git-worktrees 9opencode 9
Agent
CLI-backed mechanical implementer — the agy variant of fast-worker. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the session wants the work offloaded to the agy (Antigravity) CLI backend (default model Gemini 3.6 Flash (High)) as a cheap…
Agent
Expert code review specialist. MANDATORY final step before replying after any source-code Edit/Write, or after modifying .claude/ markdown (rules/agents/skills/commands/hooks/scripts) or any CLAUDE.md file. Reviews quality, security, and maintainability. Do NOT skip when: user approved a plan, change seems small…
Agent
CLI-backed mechanical implementer — the codex variant of fast-worker. Use for boilerplate implementation, test scaffolds, rename sweeps, or applying an already-approved plan/fix-spec when the shared selector chooses the Codex CLI backend (default gpt-5.6-luna @ xhigh) instead of the in-process sonnet worker.…
Command
Validate skill quality against routing, progressive loading, and verification criteria.
Command
Deep-dive analysis of an initial proposal — research code implementation, produce an actionable roadmap and alternatives.
Command
Audit dependency security risks.
Command Cursor
Implement an approved OpenSpec change and keep tasks in sync.
Command Cursor
Archive a deployed OpenSpec change and update specs.
Command Cursor
Scaffold a new OpenSpec change and validate strictly.
Plugin Claude Code
A backend workflow package that coordinates a lead assistant with seven specialist agents for software projects.
Instructions file
A set of instructions for Octopus, a Claude Code plugin made from Markdown agents and slash commands. It runs work across other software projects and uses OpenSpec, a format for recording current system behavior and proposed changes.
Agent
A requirements-analysis agent for backend work. It turns customer messages, tickets, screenshots, or vague ideas into technical questions, assumptions, risks, and open questions.
Agent
A specification specialist in the Octopus workflow that turns clarified requirements into OpenSpec changes, structured proposals for software modifications.
Agent
A coding agent for implementing assigned changes and tests in an OpenSpec-based project. It works on feature branches and replies in Traditional Chinese.
Command
An automated build command for an OpenSpec change, where a change is a planned piece of software work. It checks the plan, has a builder implement each task, reviews the result, and automatically repairs high-priority issues for up to three rounds.
Command
A setup command for connecting an existing project to Octopus, a workflow built around OpenSpec project specifications and tracked changes. It checks the required command-line tool and project structure, surveys the codebase, and creates an Arena handover report.
Command
A requirements-planning command for OpenSpec, a tool that records software changes as proposals, specification updates, and task lists. It clarifies the request, challenges risky assumptions, and pauses for approval before implementation.
Hook
Runs before the agent uses a tool for Bash, Edit and Write tool calls, executing branch-guard.mjs and spec-status-guard.mjs via node (2 commands). From SatoruoGojoo/octopus.
Command Claude Code
Implement an approved OpenSpec change and keep tasks in sync.
Command Claude Code
Archive a deployed OpenSpec change and update specs.
Command Claude Code
Scaffold a new OpenSpec change and validate strictly.
Instructions file CodexOpenCode
AGENTS.md instructions for skoskov/mvp-operating-system, covering mvp operating system maintainer rules, startup gate, source repository role and verification.
Skill Claude CodeCodex
Run idea-to-MVP projects with idea intake, launch market research, brand/design/UX flow, standard stack preflight, memory preflight, analytics/observability planning, support planning, build/deploy/verification planning, pre-launch iteration, decision cards, token budgeting, OpenSpec, Codex implementation, independent…
Instructions file CodexOpenCode
AGENTS.md instructions for alrece/loop-engineering, covering agents.md — loop engineering ai agent behavior spec, 0. iron rules (must / must not), must, must not and 1. command execution spec.
At most 3 mods per repository are shown here — the rest are on their repository pages: