agent-harness-construction

agent-harness-construction is a skill for Claude Code from loulanyue/awesome-claude-notes. It costs 25 tokens per session (507 once invoked), scanned A, a copy of agent-harness-construction, MIT.

Guidance for designing how an AI agent chooses actions, uses tools, reads results, handles errors, and manages its available context. The aim is to make the agent more likely to finish tasks correctly.

In plain words
What is it for?
Use it to define tool interfaces, structure tool responses, plan error recovery, separate high-risk operations, and manage prompt context.
Why use it?
Poorly designed tools and unclear results can cause an agent to make unsafe choices, lose useful information, or get stuck after an error. Clear action and recovery rules make its work easier to control.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the awesome-claude-notes plugin — 106 skills, 61 commands, 28 agents shipped together

Good fit Use it to define tool interfaces, structure tool responses, plan error recovery, separate high-risk operations, and manage prompt context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/loulanyue/awesome-claude-notes/agent-harness-construction
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add loulanyue/awesome-claude-notes --skill agent-harness-construction
Clone the repo
git clone --depth 1 https://github.com/loulanyue/awesome-claude-notes

Made for: Claude Code.

Or install awesome-claude-notes, the plugin that ships this one along with the rest of its 106 skills, 61 commands, 28 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-harness-construction

README.md
[![agentmods](https://agentmods.dev/badge/skills/loulanyue/awesome-claude-notes/agent-harness-construction/github.svg)](https://agentmods.dev/skills/loulanyue/awesome-claude-notes/agent-harness-construction)
Your own site
<a href="https://agentmods.dev/skills/loulanyue/awesome-claude-notes/agent-harness-construction"><img src="https://agentmods.dev/badge/skills/loulanyue/awesome-claude-notes/agent-harness-construction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-harness-construction

Your own site · 80×15
<a href="https://agentmods.dev/skills/loulanyue/awesome-claude-notes/agent-harness-construction"><img src="https://agentmods.dev/badge/skills/loulanyue/awesome-claude-notes/agent-harness-construction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 92% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00507
Opus 5 $0.00013 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 8d ago against content hash 62bfd5ab829e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-harness-construction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

92% identical to agent-harness-construction — 35 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

docs/ja-JP/skills/agent-harness-construction/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

原文

ナビゲーション

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 83 lines · 25 tokens per session scan A 62bfd5ab829e

Subscribe to this mod's changes

agent-harness-construction is a skill published in the GitHub repository loulanyue/awesome-claude-notes (270 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 507 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to agent-harness-construction, differing in 35 lines, and is treated as a copy.

Related

Other skills, from other repositories

swarm-pr-review

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

ZaxbyHub/opencode-swarm · 91 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

council

Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.

ZaxbyHub/opencode-swarm · 28 tokens

safe-extraction

Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.

ZaxbyHub/opencode-swarm · 60 tokens

bundle-safety

Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.

ZaxbyHub/opencode-swarm · 30 tokens

durable-session-state

Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…

ZaxbyHub/opencode-swarm · 70 tokens