harness
Agent engineering harness for any repo. Creates a short AGENTS.md table-of-contents, structured docs/ knowledge base (ARCHITECTURE, QUALITY, CONVENTIONS, COORDINATION, RESILIENCE), custom agent-readable linters (WHAT/FIX/REF format), CI enforcement, and execution plan templates. Supports Rust, Go, TypeScript, and Python. Integrates agent-motivator recovery protocols into docs/RESILIENCE.md (7-point checklist, VBR standards, failure pattern library). Use when setting up any repo for agent-first development, upgrading an existing AGENTS.md, or enforcing architectural lint gates. Includes --audit flag for tool lifecycle checks and L1/L2/L3 progressive disclosure.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bowen31337/harnessWhat This Skill Does
The harness skill is a comprehensive agent-engineering framework designed to standardize the development environment for AI agents. It implements the OpenAI Codex team's agent-first engineering pattern, transforming raw repositories into highly structured, agent-readable environments. By generating a standardized AGENTS.md table-of-contents, a robust documentation suite (including ARCHITECTURE, QUALITY, CONVENTIONS, and COORDINATION), and custom linters, it ensures that your repository provides sufficient context for autonomous agents to perform high-quality coding tasks. The skill provides a mechanism for agent-readable error reporting using a strict WHAT/FIX/REF format, allowing agents to self-correct architectural and quality regressions without human intervention.
Installation
You can install the harness skill directly into your OpenClaw environment using the following command:
clawhub install openclaw/skills/skills/bowen31337/harness
Use Cases
- Repo Scaffolding: Initialize a new repository with a complete documentation suite tailored for agent-first development.
- Architectural Enforcement: Introduce custom linting rules that prevent agents from violating repository dependency rules or naming conventions.
- Maintenance & Auditing: Use the
--auditflag to check the freshness of your tool lifecycle and thedoc_garden.pyscript to identify and repair stale documentation references. - Task Planning: Automatically generate structured execution plans for complex engineering tasks, ensuring agents follow a logical path during multi-step implementations.
Example Prompts
- "Harness the current repository. Detect the language, scaffold the necessary documentation files, and set up the agent-linting script."
- "Audit the documentation in this repo using the harness tool. Report any stale references and generate a PR to fix them."
- "I need to add a new database module. Generate an execution plan using the harness tool that adheres to our ARCHITECTURE.md and CONVENTIONS.md standards."
Tips & Limitations
- Progressive Disclosure: Utilize the L1/L2/L3 markers in your AGENTS.md to ensure agents can navigate the repository structure effectively based on the depth of the task at hand.
- Language Support: Currently, the skill is optimized for Rust, Go, TypeScript, and Python. Using it on other languages may require manual configuration of the linter scripts.
- CI/CD Integration: Always ensure that the generated .github/workflows/agent-lint.yml file is active to prevent the introduction of architectural debt, as this is the most effective way to keep your agents aligned with repository standards.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bowen31337-harness": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
Terse
Skill by bowen31337
Identity Resolver
Skill by bowen31337
agent-self-governance
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure Knowledge Logging). Use when: (1) receiving a user correction — log it before responding, (2) making an important decision or analysis — log it before continuing, (3) pre-compaction memory flush — flush the working buffer to WAL, (4) session start — replay unapplied WAL entries to restore lost context, (5) any time you want to ensure something survives compaction, (6) before claiming a task is done — verify it, (7) periodic self-check — am I drifting from my persona? (8) cost tracking — was that expensive operation worth it? (9) discovering infrastructure — log hardware/service specs immediately.
rsi-loop
Recursive Self-Improvement (RSI) loop for EvoClaw agents. Provides a structured observe→analyze→synthesize→deploy pipeline that enables agents to detect their own failure patterns and generate concrete improvement proposals (new skills, routing fixes, SOUL.md updates, memory improvements). Use when: (1) logging a task outcome (success/fail/quality), (2) running periodic self-improvement analysis, (3) reviewing or deploying improvement proposals, (4) integrating RSI into EvoClaw hub/edge agents via MQTT, (5) checking agent health score, (6) any mention of "self-improvement", "recursive improvement", "fix my own mistakes", "improvement loop", or "agent evolution". Core EvoClaw primitive.
clawchain
ClawChain RPC client for EvoClaw agents. Connects to Substrate-based blockchain, queries on-chain agent data, submits transactions, and enables agents to participate in on-chain governance and reputation tracking. Use when working with ClawChain L1 blockchain, agent DIDs, token economics, or agent reputation systems.