RepoAlerts

MicTx/spec-harness

AI skill

Can I trust it?

Be careful with this one.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change yesterday.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

Task-package workflow tool for AI coding agents. It stores long-running engineering tasks as recoverable Development Records under .spec/, with verifiable scope, per-task boundary and verify declarations, evidence, archiving, and Git gates for commit and push. It provides no…

Who it's for

Developers using AI coding agents such as Claude Code or Codex on long, multi-session changes who want scoped, verifiable task tracking

How to use it

Install

bash install.sh

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up MicTx/spec-harness in my project. Follow its README: https://github.com/MicTx/spec-harness. Explain each step and check it is safe before running anything.

Star curve

283From 0 to 283 stars between 2 Oct 2026 and 7 Nov 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![MicTx/spec-harness on RepoAlerts](https://repoalerts.com/badge/MicTx/spec-harness.svg)](https://repoalerts.com/repo/MicTx/spec-harness?ref=badge)
Share on X

  • vercel-labs/durable-harness

    Runs coding-agent harnesses (Pi, OpenCode, fx, Claude Code, Codex) as durable agents on a Workflow SDK World. Each session is a workflow run whose conversation, turns and tool calls are kept in an eve

    LibraryAI agentsTypeScript · 296 stars · +22 this week · 22 days old

  • pullboard-dev/pullboard

    A local-first coordination tool that lives in a git repo and runs multiple coding agents against a spec you approve. Agents claim items in separate worktrees, submit work behind a green gate, and a di

    CLI toolAI agentsJavaScript · 736 stars · +272 this week · 32 days old

  • makushingu/harness-maxxing

    A self-hosted web control room for Claude Code. It manages persistent Claude sessions organised by project and topic, with files, tasks, scheduled jobs, a Telegram bridge, voice transcription and a me

    AppAI agentsPython · 139 stars · +132 this week · 16 days old

  • iha2/superlite

    A Claude Code plugin that plans a software build, splits it into tasks that run in parallel, assigns each task to a model by difficulty, checks the seams between parts and reviews the result. The user

    AI agentsPython · 249 stars · +7 this week · 21 days old

  • didi/helixharness

    A framework for building a team-specific AI coding harness on Codex and Claude Code. It loads project knowledge, engineering rules and workflow into the agent across requirements, implementation, test

    AI skillAI agentsPython · 326 stars · +131 this week · 11 days old

  • google-research/harness2

    A Python framework for recursive agent harnessing, which refines the prompts, tools, memory, skills and orchestration around a fixed model. It runs a propose-probe-compose loop per task and keeps a pe

    AgentAI agentsPython · 22,955 stars · +1,436 this week · 32 days old · HN 81 pts