PreToolUse
01Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing spec-lint.mjs via node. From Go1c/LumioAgent.
20 1mo ago A
tokens not measured
original MIT
LumioAgent
02Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse).
20 1mo ago A
tokens not measured
original MIT
reviewer
03Agent
A separate code-review agent that checks a completed development task against its requirements and project rules. It looks for missing behavior, incorrect logic, security problems, and unsupported claims about testing.
20 1mo ago A 51 tokens
original MIT
Skill Claude CodeCodex
A preparation process that loads relevant project guidance and chooses how deeply to inspect the code before making changes.
20 1mo ago A 56 tokens
original MIT
Skill Claude CodeCodex
Use when starting creative work - creating features, building components, adding functionality, or modifying behavior - before any implementation. Explores user intent, requirements and design.
20 1mo ago A 36 tokens
copy · 80% MIT
Skill Claude CodeCodex
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
20 1mo ago A 38 tokens
original MIT
spec-steward
07Skill Claude CodeCodex
A repository-maintenance procedure for organizing the .spec knowledge base. It covers rules, standards, feature records, agents, and reusable skills, including their required names and metadata.
20 1mo ago A 72 tokens
original MIT
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
20 1mo ago A 17 tokens
original MIT
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
20 1mo ago A 21 tokens
original MIT
Skill Claude CodeCodex
A task-planning workflow that breaks a large or unclear development goal into smaller task cards. Each card describes its scope, dependencies, and objectively checkable acceptance conditions.
20 1mo ago A 79 tokens
original MIT
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
20 1mo ago A 17 tokens
copy · 83% MIT
Skill Claude CodeCodex
Use when starting feature work that needs isolation from current workspace, and when implementation is complete and you need to integrate the work - covers creating isolated workspaces (native tools or git worktree fallback) and finishing branches (verify, merge/PR, cleanup).
20 1mo ago A 57 tokens
original MIT
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
20 1mo ago A 43 tokens
original MIT
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task, before touching code.
20 1mo ago A 21 tokens
original MIT
Instructions file CodexOpenCode
Instructions for Go1c/LumioAgent: Compatibility entrypoint for agent tools. The authoritative spec lives under .spec/; this file only points, it defines no rules of its own.
20 1mo ago A 313 tokens
original MIT
Instructions file
Instructions for Go1c/LumioAgent: Claude Code entrypoint. The @import lines below force-load their content into every session context. The authoritative source is .spec/; this file only loads, it defines no rules of its own.
20 1mo ago A 290 tokens
original MIT
Plugin Claude Code
An add-on that connects an AI coding agent to Workflow, an online project-management system. It supports planning work, creating and checking tasks, and sending results and evidence back to the system.
2 2d ago A
tokens not measured
original MIT
workflow
18Plugin Claude Code
A plugin that connects an AI agent to Workflow, a platform for planning, sharing, tracking, and completing software tasks.
2 2d ago A
tokens not measured
original MIT
bug
19Command
A command that records a reported software bug as a recoverable local Workflow draft. It records the issue only and does not start fixing it or turn it into a development task.
2 2d ago A 20 tokens
original MIT
deps
20Command
A command that analyzes the upstream and downstream relationships of a workflow record or local draft. It creates a list of direct links, dependency chains, blockers, evidence, and confidence levels.
2 2d ago A 20 tokens
original MIT
feedback
21Command
A command for sending a problem or suggestion about the Workflow platform to its maintainers.
2 2d ago A 32 tokens
original MIT
plan
22Command
A command that turns an idea or document into a local, recoverable workflow blueprint. A workflow blueprint describes the planned work and its related objects before anything is uploaded.
2 2d ago A 22 tokens
original MIT
policy
23Command
A command for viewing or changing Workflow authorization policies. These policies control modes such as automatic approval, planning, manual approval, and full access.
2 2d ago A 16 tokens
original MIT
qa
24Command
A command for testing and accepting a Workflow issue in the real online environment. It follows a prescribed process for reproducing the issue, collecting screenshots, and recording one final result.
2 2d ago A 25 tokens
original MIT