agent-harness-construction

A skill in affaan-m/ECC · 304,842 stars on GitHub

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

Security grade of this SKILL.md: SAFE · how we grade

How to install agent-harness-construction

npx skills add affaan-m/ECC --skill agent-harness-construction -a claude-code

The skills CLI copies this one skill into Claude Code (use -a for another agent). Or read its SKILL.md on GitHub.

What the SKILL.md says

Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion. Agent output quality is constrained by: Action space quality. Observation quality. Recovery quality. Context budget quality. Use stable, explicit tool names. Keep inputs schema-first and narrow. Return deterministic output shapes. Avoid catch-all tools unless isolation is impossible. Use micro-tools for high-risk operations (deploy, migration, permissions). Use medium tools for common edit/read/search loops. Use macro-tools only when round-trip overhead is the dominant cost. Every tool response should include: status: successwarningerror. summary: one-line result. next_actions: actionable follow-ups. artifacts: file paths / IDs. For every error path, include: root cause hint. safe retry instruction. explicit stop condition. Keep system prompt minimal and invariant.

Other skills in affaan-m/ECC

  • accessibility Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels, accessibilit…
  • agent-architecture-audit Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discip…
  • agent-eval Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metr…
  • agent-introspection-debugging Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when…
  • agent-payment-x402 Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwal…
  • agent-runtime-gateway-smoke-test Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connec…
  • agent-security-hardening Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime ide…
  • agent-self-evaluation Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conc…
  • agent-sort Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY b…
  • agentic-engineering Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engi…
  • agentic-os Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based me…
  • ai-first-engineering Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, revie…
  • ai-regression-testing Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check work…
  • android-clean-architecture Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and…
  • angular-developer Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices…
  • api-connector-builder Build a new API connector or provider by matching the target repo's existing integration pattern exactly. Use when adding one more integrat…
  • api-design REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for…
  • architecture-decision-records Capture architectural decisions as numbered ADR markdown files in docs/adr/ with context, alternatives considered, consequences, and an ind…
  • article-writing Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied…
  • automation-audit-ops Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP…