---
name: Harness Help
slug: harness-help
category: AI Engineering
description: Harness Help explains what the Agentsmith harness does, which profile you’re on, the main rules, and the current safety mode. Use it when you need a plain-language starting point or want to know what to do next.
github: "https://github.com/PromptPartner/agentsmith/tree/master/skills/harness-help"
language: Python
stars: 185
forks: 5
install: "npx degit https://github.com/PromptPartner/agentsmith/tree/master/skills/harness-help ~/.claude/skills/harness-help"
installs_to: ~/.claude/skills/harness-help
source_path: skills/harness-help/SKILL.md
collection_size: 13
category_size: 3278
collection_url: "https://dirskills.com/collections/PromptPartner/agentsmith"
added: 2026-09-06T05:20:49.244Z
last_synced: 2026-09-06T05:20:49.244Z
canonical_url: "https://dirskills.com/skills/harness-help"
---

# Harness Help

Harness Help explains what the Agentsmith harness does, which profile you’re on, the main rules, and the current safety mode. Use it when you need a plain-language starting point or want to know what to do next.

**Install:**

```bash
npx degit https://github.com/PromptPartner/agentsmith/tree/master/skills/harness-help ~/.claude/skills/harness-help
```

## README

# Harness help — get oriented

Explain, in plain language with no jargon, what this harness does for the operator and what to do
next. This is the non-coder's front door.

## When this fires
"what is this harness / what does it do?" / "what are my rules?" / "which profile am I on?" /
"what do I type next?" / a general "help me get started here".

## Identify the target
Use the agent named by the operator or the explicit `AGENTSMITH_AGENT` value. Never infer the active
agent from this skill's install path: portable canonical content may be copied into a required
client adapter such as `.claude/skills`. Without a declared agent, explain the common rules and
label agent-specific safety configuration as unknown.

## What to do (no script needed)
Read the canonical managed block in `AGENTS.md` and report:
1. **Active profile(s)** — the work-type this project is tuned for (from the profile section).
2. **Your rules, in 3–5 bullets** — the load-bearing ones (verify before done, protected main,
   look before you delete, be honest about what failed). Summarize; don't dump the file.
3. **Safety mode** — when an agent is declared, read its managed native configuration and explain
   the effective approval and sandbox settings. Otherwise say that client-specific safety was not
   identified.
4. **What to type next** — take one small task end to end. Say “verify” or “handoff”; mention an
   invocation prefix only when the declared client documents one.

Point to `docs/01-harness-philosophy.md` and `docs/07-how-to-pick-a-profile.md` for the why and the
profile choices. If `FIRST-STEPS.md` exists, point at it too.

## Report
A short, friendly orientation: the selected agent when known, profile, a few rules, safety mode,
and the one thing to do next. No file dumps, no jargon.