Zeroshot — Development skill for Claude Code
Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and nothing ships until the checks pass.
How to install Zeroshot
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the-open-engine/zeroshot and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Zeroshot does
Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and nothing ships until the checks pass. Works with Codex, Claude Code and Copilot.
Alternatives in Development
- Understand Anything — Graphs that teach graphs that impress 80.7k ★
- Agentlas Build — Build, repair, or package Agentlas agents and teams with Hephaestus 1.1k ★
- Cavemem — Frozen — cross-agent persistent memory for coding assistants 674 ★
README
[](https://github.com/the-open-engine/zeroshot/releases/latest) [](https://www.npmjs.com/package/@the-open-engine-company/zeroshot) [](https://github.com/the-open-engine/zeroshot/actions/workflows/ci.yml?query=branch%3Amain) [.
Makoto
When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deed
Dev Cycle
Orchestrates the development cycle - developer implements, reviewer critiques, repeat until done
Debug Pro
Resolve existing defects through adaptive evidence gathering, exact reproduction, causal confirmation, bounded
Codeword Silly Goose
A Claude skill that catches leaked secrets, refuses to repeat them, and calls you a silly goose until you rota
Plan Consensus
Run plan-consensus skill — Claude↔Codex independent-critic review on a plan file until consensus or impasse
Related Agents
Playwright API Test Healer
Use this agent to diagnose and repair one failing request-level test — REST or GraphQL, including schema-valid
Developer Overview
code-container (container) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode
Coder Teammate
Code implementation teammate. Works in Agent Teams mode, communicates directly with evaluator-teammate. Claims