strikethroo

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

Why Strikethroo?

Bends to your conventions Plain-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 agent Every 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 keys Runs 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 skills The workflow ships as Agent Skills: one SKILL.md works on any harness supporting the format. Install once; the right skill auto-loads when you describe what you need.

Adapts to every codebase

Every codebase has its own conventions, and Strikethroo bends to them instead of imposing its own. Three plain-Markdown surfaces -- no plugins, no code:

Hooks

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.

Templates

Define the shape of plans and tasks -- add your own sections and checklists.

Project context

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.

Quick Start

# 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.

In your coding assistant

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:

Step	Skill	Output
Plan	/st-create-plan <your prompt>	.ai/strikethroo/plans/64--auth/plan-64--auth.md
Tasks	/st-generate-tasks 64	.ai/strikethroo/plans/64--auth/tasks/*.md
Execute	/st-execute-blueprint 64	Working code, one commit per phase

Human review gates between steps catch scope creep before any code is written. Each step runs with clean context -- the planning agent sees only the work order, the task agent sees only the approved plan, and each execution sub-agent receives only its specific task.

See the Workflow Guide for the full step-by-step with advanced patterns. Once a plan exists, visualize its plans, tasks, and dependency graph in Visualizations.

Visualize the data

Strikethroo comes with an optional web application to help you visualize your plans, tasks, and progress. No installation necessary, just execute the following command in a project using Strikethroo:

npx strikethroo serve

This will open a web page that will help you navigate your plans and their tasks, present or archived.

Plans board	Plan detail page	Archive

Documentation

• Workflow Guide -- Step-by-step workflow with visual guides
• Customization Guide -- Hooks, templates, and project context
• Reference -- Glossary and CLI reference
• FAQ -- Answers to common questions
• Visualizations -- See plans, tasks, and the dependency graph
• Migrating from 1.x -- Upgrade from slash commands to Agent Skills