# Chachamaru127/claude-code-harness

Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle

Repository: https://github.com/Chachamaru127/claude-code-harness
Canonical: https://ross.abutalabs.com/products/claude-code-harness
Language: Shell
License: MIT
License Family: permissive
Last push: 2026-08-25T18:34:01+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 18
- inputs: {"age_days": 264, "days_push": 8, "days_rel": 8, "gap_med": 0, "n_releases_24m": 200}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3072, forks 301 (observed 2026-08-28T04:07:41.617828+00:00)

## What it is
A development harness plugin for Claude Code (and Codex CLI, Cursor, Grok) that enforces a disciplined Plan→Work→Review→Release loop with specs, gates, and guardrails around AI coding agents. It structures agent workflows so plans are approved, implementations are verified, reviews are independent, and release evidence is packaged automatically.

## Use cases
- enforce a plan-approve-implement-review workflow for claude code
- stop ai coding agents from drifting off plan
- add guardrails and gates around ai-generated code
- generate specs and plans before letting an agent code
- package release evidence automatically after agent work
- run independent code review of ai-written changes
- make ai coding workflows repeatable across different agent tools

## When to choose
- you use Claude Code, Codex CLI, Cursor, or Grok for serious development work
- you want spec-driven, gated delivery loops instead of ad-hoc agent prompting
- you need review and verification stages enforced before code ships

## When to avoid
- you only want quick one-off code completions without process overhead
- you don't use any supported AI coding agent
- you prefer lightweight prompt-based workflows without structured gates

## Facets
- artifact type: plugin
- maturity: active
- function: workflow-automation, developer-tools, agent-framework, code-review, testing, ci-cd
- domain: developer-tools, large-language-models, testing
- platform: cli, cross-platform
- tags: claude-code, ai-coding-agents, plan-work-review-loop, spec-driven-development, guardrails, codex-cli, cursor, go-core, skills, automation, ai-agents, shell

## Member repositories
- Chachamaru127/claude-code-harness (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.617828+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:27:57.605014+00:00, confidence not recorded.
  - readme: https://github.com/Chachamaru127/claude-code-harness (fetched 2026-08-28T04:07:41.617828+00:00, sha bb9c9d36f8d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.