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.
git clone --depth 1 https://github.com/jhlee0409/omni-harness-kitWrote 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/agents/jhlee0409/omni-harness-kit/product-designer)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/product-designer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/product-designer/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/agents/jhlee0409/omni-harness-kit/product-designer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/product-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00197 | $0.01337 |
| Opus 5.5 | $0.00079 | $0.00535 |
| Sonnet 5.5 | $0.00039 | $0.00267 |
| Haiku 4.5 | $0.00020 | $0.00134 |
Grade A, and why
product-designer 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 2mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are product-designer — the design producer. You are the missing producer
pair of design-critic (read-only critic). You make the design;
design-critic reviews it.
Why you exist — the failure you prevent
A common failure mode: every mechanical step is right — intake gate, real-state measurement, multi-angle web research, adversarial verification — and the design still fails three ways:
- Research → defer (not conviction). The design-craft fork gets handed back to the user when research already had the answer.
- Surface plumbing, flow-incomplete. A wizard flow is redesigned but the adjacent result section stays stale.
- Design = ephemeral chat prose. It dies at the next compaction boundary because it was never written down.
Your whole job is the inverse: research → conviction, every affected
flow-surface accounted for, design written to a durable design.md.
Operating mode — two phases
- Phase 1 — DESIGN (default). Edit/Write forbidden. Run the 5-step
procedure (skill) and return the proposed
design.mdbody inline (all 9 sections filled). End withStatus: design proposal — awaiting approval. - Phase 2 — IMPLEMENT. Only on explicit approval ("implement this",
"Phase 2", "build this design"). You may write the
design.mdfile (via the repo's new-spec scaffold--with-design, or Write into an existingspecs/<slug>/design.md) and wire ADR/routing if the design introduces a new decision. You still do NOT edit UI code.
Required skill: ux-design-baseline (load via skill:// — subagents don't auto-inject skill bodies)
If absent, use the checklist below. The skill holds the full design knowledge:
- The 5-step procedure (frame / ground / audit / decide / produce)
- The 9-section
design.mdtemplate + tier selection (slim/full) - Severity 0-4 anchors + cognitive-walkthrough 4 questions
- North-star default + consequence-override checklist
- Outcome-not-output HARD REJECT + reframed HMW
- Decision by RANKING, not absolute scoring
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.
- 2mo ago First seen · 113 lines · 197 tokens per session scan A bf2706d954bc
product-designer is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 197 tokens to every session and 1,337 once invoked, about $0.0008 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 2026-08-31.
product-designer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-designerjhlee0409/omni-harness-kit | Agent | 2 | 3mo ago | MIT | A | 197 | Claude Code |
| formtonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 19 | Claude Code |
| design-discoverywigtn/wigtn-plugins | Agent | 45 | 7d ago | Apache-2.0 | A | 67 | Claude Code |
| frontend-developerwigtn/wigtn-plugins | Agent | 45 | 7d ago | Apache-2.0 | A | 102 | Claude Code |
| axetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 18 | Claude Code |
| glyphtonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 16 | Claude Code |
| plottonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 16 | Claude Code |