By e0ipso
Manage the full Strikethroo workflow: create plans from project context, decompose into atomic tasks, execute tasks with lifecycle hooks and validation gates, and refine plans by pressure-testing for gaps.
Create a new Strikethroo plan for this repository. Use when the user asks to draft, plan, or scope a new strikethroo plan — discovers the local .ai/strikethroo root, runs the project's plan hooks, gathers clarifications, allocates the next plan ID, and writes a Markdown plan conforming to PLAN_TEMPLATE.md. Do not use for generic brainstorming or work outside Strikethroo.
Execute a Strikethroo plan blueprint for this repository. Use when the user asks to run, implement, or carry out a specific plan ID — discovers the local .ai/strikethroo root, resolves the plan, validates or auto-generates tasks and the execution blueprint, optionally creates a feature branch, runs phases with lifecycle hooks, enforces validation gates, appends an execution summary, and archives the completed plan. Do not use for generic development work outside Strikethroo.
Execute a single task from a Strikethroo plan. Use when the user asks to run, implement, or carry out one specific task ID within a plan — discovers the local .ai/strikethroo root, resolves the plan, validates the task file, checks status and dependencies, runs pre-execution hooks, deploys an agent, updates status, documents noteworthy events, and emits a structured Task Execution Result. Do not use for generic development work outside Strikethroo.
Execute the complete Strikethroo workflow from plan creation through blueprint execution for this repository. Use when the user asks to run the full end-to-end workflow for a work order — discovers the local .ai/strikethroo root, creates a plan, generates atomic tasks, and executes the blueprint, all in a single uninterrupted sequence. Do not use for individual plan creation, task generation, or blueprint execution; use the dedicated skills for those.
Generate atomic Markdown tasks for an existing Strikethroo plan in this repository. Use when the user asks to decompose a specific plan ID into tasks — discovers the local .ai/strikethroo root, resolves the plan, runs the project's task-generation hooks, allocates sequential task IDs, and writes one task file per atomic unit conforming to TASK_TEMPLATE.md. Do not use for generic project planning or work outside Strikethroo.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Spec-driven development that fits each codebase like a glove.
Plain-Markdown hooks teach the agent your conventions, so every plan, task, and run inherits them. No API keys, no extra tools to run.
Workflow · Customization · Visualizations · FAQ
Bends to your conventionsPlain-Markdown hooks fire at nine points across the workflow; inject your test commands, standards, and domain rules so every plan, task, and run inherits them. No plugins, no code. |
Clean context per agentEvery step runs with a fresh, focused context: the planner sees only your work order, the task generator only the approved plan, each execution sub-agent only its single task. No context bleed, no drift. | |
No API keysRuns inside the assistant you already use -- Claude Code, Codex, Cursor, OpenCode, or Copilot -- on the subscription you already pay for. Nothing to provision, host, or rotate. |
Harness-agnostic skillsThe workflow ships as Agent Skills: one |
Every codebase has its own conventions, and Strikethroo bends to them instead of imposing its own. Three plain-Markdown surfaces -- no plugins, no code:
Fire at nine points across the workflow (before planning, after each phase, on errors, and more). Drop in your test commands, coding standards, and domain rules; every plan, task, and execution run inherits them.
Define the shape of plans and tasks -- add your own sections and checklists.
One file of domain knowledge every step reads.
Hooks, templates, and a project-context file are all plain Markdown -- nothing to compile, no plugin API to learn. See the Customization Guide for examples.
# 1. Bootstrap the shared workspace
npx strikethroo init --harnesses claude
# 2. Install the workflow skills
npx skills add e0ipso/strikethroo
Requires Node.js 22+ and an assistant that supports the Agent Skills format.
flowchart LR
A[Work Order] --> B[Plan]
B --> C{Review}
C -->|Edit| B
C -->|Approve| D[Tasks]
D --> E{Verify}
E --> G[Execute]
G --> H{Review}
H -->|Edit| G
H -->|Approve| J[Done]
Three steps, each delivered as an Agent Skill that loads when you describe what you need:
npx claudepluginhub e0ipso/strikethrooIterative plan review and execution workflow for Claude Code
Plan and autonomously build a software task end-to-end. Recons the codebase, applies preloaded memory, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste /goal command — one paste between you and done — that drives execution to completion with built-in retry, fix-spec recovery, and per-phase memory writeback. Works on Claude Code and Codex.
Turn broad Codex and Claude Code work into pressured /goal runs with oracles, local boards, receipts, and verification.
AI-powered cascading development framework with design document system and multi-agent collaboration. Breaks down projects into Features (Mega Plan), Features into Stories (Hybrid Ralph), with auto-generated technical design docs, dependency-driven batch execution, Git Worktree isolation, and support for multiple AI agents (Codex, Amp, Aider, etc.).
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claim