Analyze GitHub issues and implement AI-generated solution plans (pure plugin - no Python required)
Analyzes ONE GitHub issue and generates 2-4 solution plans. Optimized for single-issue focus with aggregation-friendly output. For multiple issues, spawn separate issue-blaster agents in parallel. Use when user wants to solve an issue, fix a bug, implement a feature from a GitHub issue, create implementation plans, or compare solution approaches. Triggers on: solve issue, analyze issue, create plan for, fix issue #, generate options for issue.
Implements a chosen solution plan by creating a git worktree and making commits. Use when user wants to implement a plan, execute an option, apply a solution, or proceed with implementation. Triggers on: implement plan, execute option, go with option, apply plan, proceed with.
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Reusable subagent definitions for common development workflows
Parse and analyze Workato recipe JSON exports for logic, data flow, field mappings, error handling, and control flow
Interact with Namecheap API for domain and DNS management
Spec-Driven Development toolkit — generate thorough specs, plans, and tasks for any project
Browser automation skill with persistent page state for developers and AI agents
npx claudepluginhub grailautomation/claude-plugins --plugin issue-blasterFetches GitHub issue details to create comprehensive implementation specifications, analyzing requirements and planning structured approach with clear implementation steps.
Auto-fix GitHub issues by analyzing issue details and implementing solutions
For easy problems, start here. For harder problems, do this after Explore.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).