Skip to content
View Ancienttwo's full-sized avatar
14 followers · 8 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: Starstruckx2Achievement: YOLO

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: Starstruckx2Achievement: YOLO

Block or report Ancienttwo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Ancienttwo/README.md

Ancienttwo — Reliable Agent Systems

Building reliable agent systems for real software work.

I design developer tools that make AI-assisted engineering repeatable, inspectable, and resumable across Claude Code, Codex, and agentic runtimes. My work focuses on file-backed workflows, fail-closed architecture controls, and evidence a human can actually review.

Selected systems

Project What it does
repo-harness Turns coding-agent sessions into a repeatable repo-local workflow with plans, checks, handoffs, and review evidence.
Fable-agents Routes orchestration, execution, deep reasoning, and ship gates across specialized Claude models and Codex.
ArchContext Embeds an architecture control loop into agentic coding runtimes, with local-first and fail-closed boundaries.
Agent Auditor Produces evidence-backed audits for AI agents, Claude Code setups, and Claude Agent SDK applications.

Current focus

  • Reliable coordination between coding agents and human review
  • Local-first architecture enforcement with explicit failure boundaries
  • Agent evaluation grounded in repositories, traces, and reproducible checks

Start with repo-harness  ·  Explore all repositories

Pinned Loading

  1. repo-harness repo-harness Public

    File-backed workflow harness for reliable Claude Code and Codex sessions.

    TypeScript 391 24

  2. Fable-agents Fable-agents Public

    Portable model routing for Claude Code, specialized agents, ship gates, and Codex.

    Shell 35

  3. arch-context arch-context Public

    Local-first architecture control loop for agentic coding runtimes.

    TypeScript 1

  4. agent-auditor agent-auditor Public

    Evidence-backed audits for AI agents, Claude Code, and Agent SDK applications.

    1

  5. xiaohongshu-skill xiaohongshu-skill Public

    Execution-grade Xiaohongshu operations skill for Codex, OpenClaw, and agencies.

    Python 2

  6. growth-hacker growth-hacker Public

    Local-first dashboard for social growth workflows powered by Hermes and OpenClaw.

    TypeScript 1