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 naveedharri/benai-skills --skill pick-my-harnessgit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/pick-my-harness)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/pick-my-harness"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/pick-my-harness/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/naveedharri/benai-skills/pick-my-harness"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/pick-my-harness.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 | $0.00158 | $0.00961 |
| Opus 5 | $0.00079 | $0.00481 |
| Sonnet 5 | $0.00032 | $0.00192 |
| Haiku 4.5 | $0.00016 | $0.00096 |
Grade A, and why
pick-my-harness 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick My Harness
Turns "which app should I use" into one named recommendation. A model is only half a local AI setup; this picks the app that gives it skills, MCP servers and your files.
Before you start
Run the check in references/environment-check.md first. These skills need a shell on the user's own machine. If the environment is a sandbox or container, stop and tell the user to run this in Claude Code on the computer they want to set up. Do not report detected specs from a sandbox: wrong specs are worse than none.
Steps
Track progress:
Task Progress:
- [ ] 1. Ask the four questions
- [ ] 2. Match against the matrix
- [ ] 3. Name one tool and its limits
- [ ] 4. Render the HTML report
1. Ask the four questions
Ask all four at once, as a short numbered list, in plain language. Never ask about VRAM here.
- What is the main job: chatting with documents, writing code, general chat, or running automated tasks?
- Is this just for you, or for a team who all need access?
- How comfortable are you editing a config file if it unlocks more control? (happy / rather not)
- Does everything need to stay on your machine with no cloud fallback?
If the user already answered some in their request, do not re-ask. Use what they gave.
2. Match against the matrix
Apply the decision rules in references/harness-matrix.md. That file holds the six tools, their real capability flags, and the tie-breakers.
3. Name one tool and its limits
Output exactly one recommendation, never a shortlist. Give: the tool, one sentence on why it won for their answers, its three capability flags, and one line on what it cannot do. Then give the single command or download link to get it.
If their answers make a second tool genuinely necessary alongside the first (most commonly LM Studio underneath something else), say so explicitly as a pair rather than presenting a choice.
4. Render the HTML report
Deliver the recommendation as a rendered HTML page, not as chat text. Build it from references/report-template.md using the pick-my-harness layout in section 4, save it to the Desktop, and open it. Keep the chat reply to two lines plus the file path.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 66 lines · 158 tokens per session scan A e003f09e69f4
pick-my-harness is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 158 tokens to every session and 961 once invoked, about $0.0008 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 2026-09-05.
Other skills, from other repositories
ai-prompting-basics
A practical guide to writing clearer requests for Claude, an AI assistant, by adding context, examples, roles, and output rules.
openrouter-models
Choose among the hosted models the shared router serves — discover current ids and prices from the public catalog, self-enforce a spend budget the router does not meter for you, respect the free-tier prompt-logging caveat, and request onboarding of a model the router does not serve yet.
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…
daily-ai-brief
Run the AI-news crew (scout, analyst, editor) to sweep the field with web search and ship a ranked briefing. Trigger when the user asks for an AI news brief, a daily or weekly AI roundup, "what shipped in AI", a model-release recap, or wants the standing cadence run.
scan-releases
Scan official AI release notes, changelogs, and deprecation pages, then flag what affects the user's stack and recommend an action for each item. Trigger on requests like "what AI releases happened recently," "check if my models or tools are deprecated," "any changelog updates that affect my stack," or periodic…
flash-attention
Speed up long-sequence transformer training and inference.