agent-harness-design

agent-harness-design is a skill for Claude Code from AnastasiyaW/codex-claude-code-config. It costs 195 tokens per session (668 once invoked), scanned A, original, MIT.

A set of reference guides for designing coding agents, their tools, permissions, budgets, safety checks, and evaluation. An agent harness is the surrounding system that controls how an agent acts and is observed.

In plain words
What is it for?
Use it to design tool permissions, draft-and-approve workflows, context trust labels, spending limits, traces, incident reviews, and tests for agent behavior.
Why use it?
It helps prevent unsafe tool use, prompt-injection mistakes, uncontrolled spending of resources, and changes that cannot be audited. It also provides ways to test whether the agent behaves correctly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the claude-code-config plugin — 57 skills, 8 agents shipped together

Good fit Use it to design tool permissions, draft-and-approve workflows, context trust labels, spending limits, traces, incident reviews, and tests for agent behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anastasiyaw/codex-claude-code-config/agent-harness-design
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 AnastasiyaW/codex-claude-code-config --skill agent-harness-design
Clone the repo
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 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-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/agent-harness-design/github.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/agent-harness-design)
Your own site
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/agent-harness-design"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/agent-harness-design/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-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/agent-harness-design"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/agent-harness-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 668 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00195 $0.00668
Opus 5 $0.00097 $0.00334
Sonnet 5 $0.00039 $0.00134
Haiku 4.5 $0.00019 $0.00067

Measured 9d ago against content hash 3ba138d64b5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-harness-design 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 9d 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.

skills/agent-harness-design/SKILL.md · 23 lines

What it actually says

Agent Harness Design

Eleven operational reference sheets for designing a safe, observable agent harness. They are situational — load only the one(s) relevant to the current task from references/ (this is why they live in a skill rather than always-on rules: building an agent harness is occasional, so the detail should not bloat every session's context).

  • references/agent-tool-design.md — 15-class risk taxonomy, 7-type permission decision object, draft/commit naming, structured tool results, deferred tool loading, hosted vs client tools, connector code-execution pattern.
  • references/context-trust-labels.md — trusted / semi_trusted / untrusted labels + verbatim boundary statement; prompt-injection defense.
  • references/agent-budgets.md — 10 mandatory budget types every agent loop must declare.
  • references/agent-evals.md — 13 eval categories + 13 adversarial test cases + when to add regression evals.
  • references/agent-observability.md — 16 trace fields per model call, 7-question audit, 6-step incident response.
  • references/agentic-rag-model-policy.md — self-improving agentic RAG state, specialist roles, evaluation vectors, Pareto selection, OpenAI model/effort policy, and Programmatic Tool Calling adoption gates.
  • references/agent-plan-artifact.md — planning mode, plan artifact format (10 fields), plan-validate-execute.
  • references/agent-approval-records.md — approval request/result JSON schemas, scope/expiration, no self-approval.
  • references/agent-streaming.md — buffering for incremental tool calls when stream=True; abort handling; output guardrail modes.
  • references/agent-event-model.md — 13 typed events for harness state persistence (replay/audit/compaction/evals).
  • references/agent-skill-install-checklist.md — pre/during/post install + audit + incident response for 3rd-party skills.

Source: distilled from the agents-best-practices skill (Denis Sergeevitch, MIT) + Anthropic harness-design engineering. Read the specific reference before applying — do not work from this index alone.

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. 9d ago First seen · 23 lines · 195 tokens per session scan A 3ba138d64b5f

Subscribe to this mod's changes

agent-harness-design is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed today), licensed MIT. It adds 195 tokens to every session and 668 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.