Back to directory

Strikethroo

A spec-driven task-management tool for AI coding assistants such as Claude Code, Codex and Gemini CLI, built around reviewing an agent's plan before it writes code rather than reviewing the resulting diff afterward.

Visit website (opens in a new tab)strikethroo.canpicasoft.com
Strikethroo

Strikethroo is a spec-driven task-management tool for AI coding assistants such as Claude Code, Codex and Gemini CLI. It is built around an explicit approval gate: the user reviews the agent's plan, one question at a time, before code is written, on the reasoning that correcting a plan costs a sentence while correcting the same misunderstanding in a finished diff costs a full review and rework cycle.

An optional review step runs on a different agent harness than the one that wrote the code, so the harness that produced the code is excluded from reviewing it; the reviewer only reports findings rather than fixing them itself. Workflow rules, such as a certification check that an uncertified review is never reported as clean, are compiled rather than left as editable Markdown requests, while plain-Markdown hooks at eleven points in the workflow let a team add its own test commands, standards and conventions.

It ships as a harness-agnostic Agent Skill, uses no separate API keys, and is written in TypeScript under the MIT license.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.