Skill Claude CodeCodex
This skill should be used when creating, reading, or updating devloop plans in .devloop/plan.md, task tracking, progress logs, phase management, PR feedback.
Skill Claude CodeCodex
This skill should be used when creating, reading, or updating devloop plans in .devloop/plan.md, task tracking, progress logs, phase management, PR feedback.
Skill Claude CodeCodex
Create a devloop workflow plan with autonomous exploration and task breakdown.
Skill Claude CodeCodex
This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns.
Skill Claude CodeCodex
Quick inline code review for devloop plan changes or PR diffs.
Skill Claude CodeCodex
Execute an epic plan phase-by-phase, inline by default with opt-in worker spawns per task annotation.
Skill Claude CodeCodex
Execute plan tasks via fresh-context subagents (swarm mode).
Skill Claude CodeCodex
Execute plan tasks autonomously until completion.
Skill Claude CodeCodex
Devloop commit and PR creation with validation for completed plan work.
Skill Claude CodeCodex
Configure the devloop statusline for Claude Code.
Plugin Claude Code
Generate amazing diagrams using text-based formats (SVG, Mermaid, Excalidraw, D2) with intelligent format routing and a shared design system.
Skill Claude CodeCodex
Generate diagrams using D2 (Terrastruct) -- a modern, clean diagram scripting language with excellent auto-layout. Use when the diagram-router selects D2, or when the user wants clean architecture diagrams, nested containers, or prefers D2's aesthetic. Requires the d2 CLI binary.
Skill Claude CodeCodex
Shared design principles for all diagram formats -- color theory, composition, typography, accessibility, and quality standards. Referenced by format-specific skills (svg, mermaid, excalidraw, d2). Use when generating any visual diagram to ensure professional quality.
Skill Claude CodeCodex
Automatically select the best diagram format (SVG, Mermaid, Excalidraw, D2) and diagram type based on user intent. Use when the user asks to create, draw, visualize, or diagram something and has not specified a format. Routes to the appropriate format-specific skill.
Skill Claude CodeCodex
Generate diagrams with a hand-drawn whiteboard aesthetic by writing .excalidraw files directly. Use when the user wants informal sketches, whiteboard-style visuals, or diagrams they can open and edit in Excalidraw. Saves a local .excalidraw file -- viewing/rendering is handled separately.
Skill Claude CodeCodex
Generate diagrams using Mermaid syntax -- the most LLM-friendly text-based diagram format. Use when the diagram-router selects Mermaid, or when diagrams will live in GitHub/GitLab markdown, documentation, or when quick generation with broad diagram type coverage is needed. Renders natively on major platforms.
Skill Claude CodeCodex
Generate professional-quality diagrams as raw SVG. Use when the diagram-router selects SVG, or when the user needs pixel-precise control, custom visuals, threat models, comparisons, Venn diagrams, or any diagram type that other formats cannot handle well. SVG is the most expressive format -- unlimited visual…
Plugin Claude Code
Integration with Forge, a headless agent job runner. Submit jobs to LLM agents (Claude, Gemini, Ollama, LM Studio), track status, and retrieve output via MCP tools.
MCP server Claude CodeCodexCursor +2
MCP server "forge" as configured in Zate/cc-plugins. Launched with forge mcp.
Skill Claude CodeCodex
How to use Forge to submit headless agent jobs, check status, and retrieve output via MCP tools. Use when the user wants to delegate work to a background agent, run a task on another LLM, or interact with forge.
Plugin Claude Code
Static correctness linter and quality orchestrator for Claude Code plugins, skills, and hooks. Catches invalid hook schemas, bad frontmatter, YAML corruption, and token inefficiency. Delegates description quality to skill-creator.
Skill Claude CodeCodex
Lint and audit a Claude Code plugin, skill, or hook for correctness, token efficiency, and quality. Runs static analysis against verified Claude Code internals, then delegates to skill-creator for description optimization and eval benchmarking. Use when reviewing plugin changes, writing new hooks/skills, debugging a…
Plugin Claude Code
Hybrid security scanner: deterministic SAST tools (Semgrep, Gitleaks, Trivy) for detection, LLM for triage. Includes baselining, suppression workflow, profile-aware severity, and zero-dependency fallback mode.
Agent
Triage static analysis findings using CWE-specialized criteria. Classifies findings as true positives, false positives, or needs review. Never scans code directly -- only assesses tool output. Use when: Security scan has produced raw findings that need triage. Do NOT use when: User wants to explore code, write tests…
Skill Claude CodeCodex
OWASP ASVS 5.0 requirements database for security audits. Provides chapter structure, control objectives, and verification requirements for all 17 ASVS domains.