AGENT SKILL

harness-init-runner

Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use `aios-harness` instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.

License 许可
MIT
所属仓库
rexleimo/aios
最近更新
2026-11-07
Stars
★ 62
Forks
11

01 前言 Front Matter

name
harness-init-runner
tags
[ "harness", "bootstrap", "runner", "cli", "node", "agents" ]
scopes
[ "global", "project" ]
clients
[ "codex", "claude", "gemini", "opencode", "hermes", "workbuddy", "pi", "zcode", "qoder" ]
description
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use `aios-harness` instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
repoTargets
[ "codex", "claude", "gemini", "opencode", "hermes", "agents", "workbuddy", "pi", "zcode", "qoder" ]
defaultInstall
{ "global": false, "project": false }
installCatalogName
harness-init-runner

02 资源文件 15

03 SKILL.md 正文

Harness Init Runner (Node.js)

Working directory: any Node.js repo with package.json

Create a portable long-running-agent harness inside the current repo (Node.js), without pulling in the full AIOS workspace layout.

When to use (even if AIOS is installed)

  • Use this when you want a repo-local, lightweight harness/ runner that works across Codex / Claude Code / Gemini / opencode.
  • If you already use AIOS, you may not need this. However it can coexist: this skill creates harness/ + /.harness/ and does not depend on scripts/aios.mjs.

What this skill generates (repo root)

  • harness/ (runner code)
  • harness.config.json (provider command templates)
  • /.harness/ (runtime artifacts root; gitignored)
  • package.json scripts: harness:run, harness:doctor
  • dependency: zod

Runtime artifacts are written under ./.harness/runs/* and MUST NOT be committed.

Preconditions

  • Run from (or inside) a Node.js repo that has a package.json.
  • If package.json is missing, stop and ask the user whether to create a Node project first.

Init Steps (deterministic)

  1. Locate repo root by searching upward for package.json.
  2. Copy the bundled templates from assets/template/ into the target repo root:
    • copy assets/template/harness/ → <repoRoot>/harness/
    • For harness.config.json: if the file already exists, merge (preserve user's existing keys, add only missing ones). If it does not exist, copy the template. Never silently overwrite user edits.
  3. Append /.harness/ to <repoRoot>/.gitignore (create file if missing).
  4. Update <repoRoot>/package.json (additive only):
    • Add scripts:
      • harness:run: node harness/run.mjs
      • harness:doctor: node harness/doctor.mjs
    • Add dependency zod (use dependencies unless the repo clearly wants devDependencies).
  5. Run npm install.
  6. Verify:
    • npm run harness:doctor
    • npm run harness:run -- --provider codex --task "hello harness"

Safety defaults

  • The runner performs a lightweight “human gate” check on the task text for auth/payment/policy + sensitive command keywords.
  • If blocked, it exits with a non-zero code and prints reasons.
  • Operator can bypass using --allow-risk.

Notes for multi-client compatibility

  • The runner shells out to provider CLIs; exact CLI flags vary by tool/version.
  • Default provider configs are intentionally minimal; users should adjust harness.config.json for their environment.

04 同仓库更多 Skills

rexleimo
rexleimo/aios

versioning-by-impact

Use when completing a task and deciding whether repository changes require a semantic version bump and changelog entry before commit/push.

★ 62
rexleimo
rexleimo/aios

verification-loop

Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.

Skill与智能体开发
★ 62
rexleimo
rexleimo/aios

typesafe-ai

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.

开发工程师Skill与智能体开发
★ 62
rexleimo
rexleimo/aios

skill-opt-lite

Train and optimize skill documents using the SkillOpt methodology — the agent acts as both target and optimizer, running tasks, reflecting on failures, proposing edits, and validating improvements in a self-contained training loop. TRIGGER: optimize skill, train skill, improve skill, skill training, skill optimization, SkillOpt, skill evolution, skill iteration loop, skill feedback loop, skill tuning.

Skill与智能体开发
★ 62
rexleimo
rexleimo/aios

skill-constraints

Enforce browser automation safety constraints — tool usage order, anti-detection rules, screenshot discipline, and human-in-the-loop checks. Use when setting up or verifying browser/MCP tool operations, NOT for every skill execution.

Skill与智能体开发
★ 62
rexleimo
rexleimo/aios

seo-geo-page-optimization

Use when improving a single page for SEO and AI answer-engine visibility (GEO), especially when you need faster first-screen conversion and clearer traffic funnels.

市场营销营销推广Skill与智能体开发
★ 62