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.
npx skills add PromptPartner/agentsmith --skill harness-helpgit clone --depth 1 https://github.com/PromptPartner/agentsmithWrote 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.
[](https://agentmods.dev/skills/promptpartner/agentsmith/harness-help)<a href="https://agentmods.dev/skills/promptpartner/agentsmith/harness-help"><img src="https://agentmods.dev/badge/skills/promptpartner/agentsmith/harness-help/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.
<a href="https://agentmods.dev/skills/promptpartner/agentsmith/harness-help"><img src="https://agentmods.dev/badge/skills/promptpartner/agentsmith/harness-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.00524 |
| Opus 5.5 | $0.00032 | $0.00210 |
| Sonnet 5.5 | $0.00016 | $0.00105 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
harness-help 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 1mo 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.
What it actually says
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:
- Active profile(s) — the work-type this project is tuned for (from the profile section).
- 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.
- 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.
- 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.
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.
- 1mo ago Changed · +1 lines 6524aa645a4f
- 1mo ago First seen · 38 lines · 79 tokens per session scan A 776dd936e4f4
harness-help is a skill published in the GitHub repository PromptPartner/agentsmith (178 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 524 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
web-animation-css-animations
CSS animation patterns - transitions, keyframes, scroll-driven timelines, @property, compositor-friendly properties, prefers-reduced-motion.
meta-config-stack-detect
Proposes an agents-inc configuration — a SeedPayload plus a report — from a repository, a stack the user describes, or a description of what they want to build. Load when seeding a configuration for a project that has none, or re-running one after its dependencies changed.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-infrastructure-replicate
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training.
ai-infrastructure-together-ai
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints.
ai-observability-langfuse
LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices.