agent-harness-construction
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Best use case
agent-harness-construction is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Teams using agent-harness-construction should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-harness-construction/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-harness-construction Compares
| Feature / Agent | agent-harness-construction | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Agent Harness Construction Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion. ## Core Model Agent output quality is constrained by: 1. Action space quality 2. Observation quality 3. Recovery quality 4. Context budget quality ## Action Space Design 1. Use stable, explicit tool names. 2. Keep inputs schema-first and narrow. 3. Return deterministic output shapes. 4. Avoid catch-all tools unless isolation is impossible. ## Granularity Rules - 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. ## Observation Design Every tool response should include: - `status`: success|warning|error - `summary`: one-line result - `next_actions`: actionable follow-ups - `artifacts`: file paths / IDs ## Error Recovery Contract For every error path, include: - root cause hint - safe retry instruction - explicit stop condition ## Context Budgeting 1. Keep system prompt minimal and invariant. 2. Move large guidance into skills loaded on demand. 3. Prefer references to files over inlining long documents. 4. Compact at phase boundaries, not arbitrary token thresholds. ## Architecture Pattern Guidance - ReAct: best for exploratory tasks with uncertain path. - Function-calling: best for structured deterministic flows. - Hybrid (recommended): ReAct planning + typed tool execution. ## Benchmarking Track: - completion rate - retries per task - pass@1 and pass@3 - cost per successful task ## Anti-Patterns - Too many tools with overlapping semantics. - Opaque tool output with no recovery hints. - Error-only output without next steps. - Context overloading with irrelevant references.
Related Skills
Writing Fuzzing Harnesses
A fuzzing harness is the entrypoint function that receives random data from the fuzzer and routes it to your system under test (SUT). The quality of your harness directly determines which code paths get exercised and whether critical bugs are found. A poorly written harness can miss entire subsystems or produce non-reproducible crashes.
attack-tree-construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
harness-model-protocol
Analyze the protocol layer between agent harness and LLM model. Use when (1) understanding message wire formats and API contracts, (2) examining tool call encoding/decoding mechanisms, (3) evaluating streaming protocols and partial response handling, (4) identifying agentic chat primitives (system prompts, scratchpads, interrupts), (5) comparing multi-provider abstraction strategies, or (6) understanding how frameworks translate between native LLM APIs and internal representations.
smc-harness
SMC trading agent skill for Alpha Harness backtesting. Provides ICT/SMC methodology, decision frameworks, and behavioral guidelines for autonomous trading in simulated environments. USE WHEN agent wakes in harness, needs to analyze markets, decide on setups, or place orders.
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
lm-evaluation-harness - LLM Benchmarking
## Quick start
BigCode Evaluation Harness - Code Model Benchmarking
## Quick Start
COBRApy - Constraint-Based Reconstruction and Analysis
## Overview
Daily Logs
Record the user's daily activities, progress, decisions, and learnings in a structured, chronological format.
Socratic Method: The Dialectic Engine
This skill transforms Claude into a Socratic agent — a cognitive partner who guides
Sokratische Methode: Die Dialektik-Maschine
Dieser Skill verwandelt Claude in einen sokratischen Agenten — einen kognitiven Partner, der Nutzende durch systematisches Fragen zur Wissensentdeckung führt, anstatt direkt zu instruieren.
College Football Data (CFB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.