What makes Iterate notable?

2.6K downloads. Trust evidence available

How should Iterate be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

Iterate

Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.6k

Updated

Oct 9, 2026

Version

3.4.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.6K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.6K downloadsadoption · observed Oct 9, 2026
Latest release: 3.4.4release · observed Oct 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s1722v1f08paw6feta6f0f11t18awbn2:iterate-skill

Install using `clawhub skill install s1722v1f08paw6feta6f0f11t18awbn2:iterate-skill` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/jingzhao-l/iterate-skill before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: iterate
slug: iterate-skill
displayName: Iterate
description: Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end.
version: 3.4.4
permissions:
  file_read: true
  file_write: true
  shell: true
  git: true
  network: "github.com only (release tarball + checksum verification)"
  sensitive_files:
    skip: [".env", ".env.*", "*.key", "secrets/", "*.pem", "*.p12", "*.crt", "*.cer", "credentials.json", ".aws/", ".ssh/"]
---

# /iterate `<goal>` `[rounds]` `[no-limit]`

# /iterate defensive `<goal>`（防御式编程模式 / Defensive-Programming Mode）

> **面向人类读者**：本文件是供 AI 助手消费的 Skill 指令。若您是开发者或浏览者，欢迎前往 GitHub 仓库 [jingzhao-l/iterate-skill](https://github.com/jingzhao-l/iterate-skill) 阅读 README，详细了解本 Skill 及其附属生态（iterate-harness、iterate-plugin、CLI 等）。
>
> **For human readers (English)**: This file is a Skill manifest consumed by AI assistants. If you are a developer or a human visitor, welcome to the GitHub repository [jingzhao-l/iterate-skill](https://github.com/jingzhao-l/iterate-skill) — read the README to learn more about this Skill and its ecosystem (iterate-harness, iterate-plugin, CLI, etc.).

---

## 简介 / Overview

> 中文：全自动多轮代码迭代。每轮从 N 个已启用维度并行审查整个项目（默认 9 个），原子问题直接修复，架构问题经用户批准后由子代理串行执行，验证通过后（合并与推送为 opt-in，默认关闭）循环直到零 findings 或达到轮数上限。
>
> English: Fully automated multi-round code iteration. Each round launches N parallel dimension reviewers across the project (default 9), fixes atomic issues directly, executes architectural issues after user approval via serial sub-agents, validates, and loops until zero findings or max rounds (merge/push are opt-in and disabled by default).

**v3.0 双模式 / v3.0 dual-mode**：本 Skill 现为**双模式**——

- **iterate 模式**（原 `/iterate`，默认，v2 全部能力完整保留）：审查 → 修复 → 验证 → 收敛闭环。
- **防御式编程模式**（新增 `/iterate defensive`）：面向**用户让 AI 做正常增量式编程任务**的场景（新增功能、修 bug、重构等），宿主 AI 从动手前到收尾**从头至尾贯彻防御式编程理念**（四步协议：pre-check → 最小步进编码 → 每步 post-check → invariant + iterate 收敛门禁），以 iterate 闭环收尾作为**交付门禁**（不收敛不交付）。

> Defensive-Programming Mode (v3.0, via `/iterate defensive`): for the scenario where the **user asks the AI to do a normal incremental coding task** (add a feature, fix a bug, refactor). The host AI performs that task end-to-end with defensive discipline — a four-step protocol: `pre-check` before touching anything → minimal-step editing (validate at the trust boundary) → `post-check` after every edit → `invariant` + the iterate convergence loop as a **delivery gate** (no convergence, no delivery).

---

## 何时使用 / When to Apply

**iterate 模式**适用于以下场景：

- 需要系统性提升代码质量、修复潜在 bug 或安全漏洞。
- 项目进入重构、迭代收尾或发布前的审查阶段。
- 需要多维度（正确性、安全、性能、架构等）并行审查。
- 希望将原子问题自动修复，将架构问题经审批后修复。

**防御式编程模式**（`/iterate defensive`）适用于**用户让 AI 做正常增量

npm-installer/README.md

# iterate-skill-installer

<p align="center">
  <a href="README.md"><strong>English</strong></a> ·
  <a href="README.zh-CN.md"><strong>简体中文</strong></a>
</p>

One-command installer for [iterate-skill](https://github.com/jingzhao-l/iterate-skill) across AI coding assistants.

[![GitHub stars](https://img.shields.io/github/stars/jingzhao-l/iterate-skill?style=social&label=Star)](https://github.com/jingzhao-l/iterate-skill)

> ⭐ If this project helps you, please consider giving a GitHub star — it means a lot to open-source maintenance!

## Usage

```bash
# Interactive install — detects your AI assistants and lets you choose
npx iterate-skill-installer

# Install to a specific assistant only
npx iterate-skill-installer --ai trae
npx iterate-skill-installer --ai claude

# Install into a project directory instead of globally
npx iterate-skill-installer --target ./my-project

# Force overwrite existing skill files
npx iterate-skill-installer --force

# Skill-only install — skip installing the iterate CLI
npx iterate-skill-installer --no-cli

# Show help / version
npx iterate-skill-installer --help
npx iterate-skill-installer --version
```

## What it does

1. Checks for Python 3 on your system.
2. Fetches the latest iterate-skill release from GitHub.
3. Downloads the release tarball and `SHA256SUMS.txt`.
4. Verifies the tarball checksum.
5. Extracts the release into a temporary directory.
6. Runs the bundled Python install script (`scripts/install.py`) which:
   - Detects installed AI coding assistants on your machine.
   - Prompts you to select targets (default: all detected assistants).
   - Copies the skill files into the correct skills directories.
7. Installs the `iterate` CLI onto your PATH (prefers `pipx`, otherwise
   `pip install --user`) so you can run `iterate onboard` directly.

> **Note:** the installer normally puts the `iterate` CLI on your PATH so a single
> command gives you both the skill and the CLI. If you **don't** want the CLI
> auto-installed, pass `--no-cli` to install the skill only — you can install the
> CLI later with `pipx install .` or `pip install .` from a checkout. If the CLI
> install fails, you can still install it later the same way.

## Supported AI assistants

Trae, Claude / Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, Gemini CLI, OpenCode, Aider, AiderDesk, Zed, Warp, Continue, Cline, Roo Code, Qoder, Augment, OpenClaw, Autohand Code CLI, IBM Bob, CodeArts Agent, Antigravity, Amp, Deep Agents, Kimi Code CLI, Astral.

## Requirements

- Node.js 18+
- Python 3.10+
- `tar` command available on PATH (available by default on macOS, Linux, Windows 10+)

## Release tarball structure

The GitHub release asset `iterate-skill.tar.gz` must contain **exactly one
top-level directory** (e.g. `iterate-skill/`). The installer extracts it with
`tar --strip-components=1`, so a tarball with multiple top-level directories,
or with entries whose path disappears after stripping the top level, is
rejected instead of being silent

README.md

# Iterate Skill

> **English** · [简体中文](./README.zh-CN.md)

<center>
  <strong>A portable, configurable AI coding assistant skill: fully automated multi-round code review and fixing.</strong>
</center>

<br/>

<p align="center">
  <a href="https://github.com/jingzhao-l/iterate-skill/blob/main/badges/downloads.json">
    <img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2Fjingzhao-l%2Fiterate-skill%2Fmain%2Fbadges%2Fdownloads.json&query=total&label=Total%20Downloads&style=for-the-badge&color=2ea44f&logo=download&logoColor=white" alt="Total Downloads">
  </a>
</p>

<p align="center">
  <a href="https://clawhub.ai/jingzhao-l/skills/iterate-skill"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2Fjingzhao-l%2Fiterate-skill%2Fmain%2Fbadges%2Fdownloads.json&query=clawhub&label=ClawHub&color=4285F4&logo=cloudflare&logoColor=white" alt="ClawHub"></a>
  <a href="https://skillhub.cloud.tencent.com/"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2Fjingzhao-l%2Fiterate-skill%2Fmain%2Fbadges%2Fdownloads.json&query=skillhub&label=SkillHub&color=624aff&logo=alibabacloud&logoColor=white" alt="SkillHub"></a>
  <a href="https://www.npmjs.com/package/iterate-skill-installer"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2Fjingzhao-l%2Fiterate-skill%2Fmain%2Fbadges%2Fdownloads.json&query=npm&label=npm&color=CB3837&logo=npm&logoColor=white" alt="npm"></a>
  <a href="./LICENSE"><img src="https://img.shields.io/badge/license-MIT-yellow" alt="License"></a>
  <a href="https://github.com/jingzhao-l/iterate-skill/releases"><img src="https://img.shields.io/github/v/release/jingzhao-l/iterate-skill" alt="GitHub release"></a>
  <a href="https://github.com/jingzhao-l/iterate-skill"><img src="https://img.shields.io/github/stars/jingzhao-l/iterate-skill?style=social&label=Star" alt="GitHub stars"></a>
</p>

> Want to support this project? A GitHub **Star** is the best thank-you and helps more developers discover iterate.

---

## Table of Contents

- [About This Project](#about-this-project)
- [At a Glance](#at-a-glance)
- [Quick Start](#quick-start)
- [Installation](#installation)
- [Usage](#usage)
- [CLI Command Reference](#cli-command-reference)
- [How It Works](#how-it-works)
- [Configuration](#configuration)
- [FAQ](#faq)
- [Security](#security)
- [Directory Structure](#directory-structure)
- [Contributing](#contributing)
- [Disclaimer](#disclaimer)
- [License](#license)

---

## About This Project

**iterate** is an open-source project that gives AI coding assistants the ability to perform **multi-round, autonomous code review and fixing**. You don't need any background about an "iterate" concept — it solves a very concrete pain point:

> AI assistants often "talk a lot but do little": a single conversation touches only a few lines, looks at one file and never re-checks the whole, a

_meta.json

{
  "ownerId": "kn72jg53khrabazt1xdtaqs8ah8awde5",
  "slug": "iterate-skill",
  "version": "3.4.4",
  "publishedAt": 1791079858627
}

scripts/requirements.txt

# iterate-skill 校验脚本与安装脚本依赖
# 许可证：MIT / Apache-2.0 / BSD 等宽松许可
jsonschema==4.26.0
PyYAML==6.0.2
rich==13.7.1

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/jingzhao-l/skills/iterate-skill",
      "sourceUrl": "https://clawhub.ai/jingzhao-l/skills/iterate-skill",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T13:00:16.526Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T13:00:16.526Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.6K downloads",
      "href": "https://clawhub.ai/jingzhao-l/iterate-skill",
      "sourceUrl": "https://clawhub.ai/jingzhao-l/iterate-skill",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T13:00:16.526Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "3.4.4",
      "href": "https://clawhub.ai/jingzhao-l/iterate-skill",
      "sourceUrl": "https://clawhub.ai/jingzhao-l/iterate-skill",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-10-04T02:10:58.627Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 3.4.4",
      "description": "**Changelog for iterate-skill v3.4.4** - Added \"kernel\" module with schema definitions, source files, tests, and data fixtures for review evidence and config validation. - Expanded test coverage with new test scripts and sample data for validation and roundtrip checks. - Updated CLI, config, and review logic for improved modularity and maintainability. - Improved documentation (README, CONTRIBUTING, SKILL.md) for clearer onboarding and usage guidance. - Internal scripts updated for publishing, validation, and automation workflows. - Removed obsolete files (e.g., skill-card.md) as part of project cleanup.",
      "href": "https://clawhub.ai/jingzhao-l/iterate-skill",
      "sourceUrl": "https://clawhub.ai/jingzhao-l/iterate-skill",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-10-04T02:10:58.627Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

npm-installer/README.md

README.md

_meta.json

scripts/requirements.txt

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data