# Agent Harness Design

> Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against prompt injection, plan-artifact, approval records, observability and traces, evals (13 categories), event model, streaming buffering, 3rd-party skill install checklist. Use when building a new Agent SDK ap…

- **Type:** Skill
- **Install:** `agentstack add skill-anastasiyaw-claude-code-config-agent-harness-design`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [AnastasiyaW](https://agentstack.voostack.com/s/anastasiyaw)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [AnastasiyaW](https://github.com/AnastasiyaW)
- **Source:** https://github.com/AnastasiyaW/claude-code-config/tree/main/skills/agent-harness-design

## Install

```sh
agentstack add skill-anastasiyaw-claude-code-config-agent-harness-design
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Agent Harness Design

Ten 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/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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [AnastasiyaW](https://github.com/AnastasiyaW)
- **Source:** [AnastasiyaW/claude-code-config](https://github.com/AnastasiyaW/claude-code-config)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-anastasiyaw-claude-code-config-agent-harness-design
- Seller: https://agentstack.voostack.com/s/anastasiyaw
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.