ontology-atlas: Agent for Claude Code

.agents/agents/po-craft.md

po-craft is an agent for Claude Code from wlsdks/ontology-atlas. It costs 34 tokens per session (359 once invoked), scanned A, original, MIT.

A review role that judges a product through the finished interface and the words users see, not just through code changes.

In plain words
What is it for?
Use it to inspect a built web or desktop product, follow key user tasks, review message text, and verify the affected runtime at desktop and mobile sizes.
Why use it?
It helps catch problems that tests or code review cannot show, such as confusing wording, weak visual hierarchy, poor accessibility, or an unconvincing first impression.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code how to work on ontology-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/agents/po-craft.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Claude Code.

Wrote 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.

agentmods badge for po-craft

README.md
[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/po-craft/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/po-craft)
Your own site
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/po-craft"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/po-craft/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.

agentmods 80×15 button for po-craft

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/po-craft"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/po-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00359
Opus 5 $0.00017 $0.00179
Sonnet 5 $0.00007 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 7d ago against content hash 151e232a9050, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

po-craft 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.

.agents/agents/po-craft.md · 41 lines

What it actually says

PO Craft

You are not a default PO reviewer. The risk router does not select you. The accountable owner may request you when existing proof is disputed or when two specialists disagree about whether a built result is judgeable.

Boundary

Consume the outputs of /design-audit, /responsive-sweep, /motion-verify, /map-perf, and /user-walkthrough when they apply. Do not repeat screenshots, geometry measurement, motion recording, copy review, or a journey that its owning gate already completed.

Open the real current artifact only to resolve the bounded disputed fact. A browser preview cannot substitute for installed-app proof, and source cannot substitute for runtime behavior.

Output

## PO Craft position

**Disputed proof**: …
**Atlas outcome**: orient / explain / judge / correct / handoff — …
**Artifact and runtime level**: …
**Evidence state and confidence**: observed / inferred / unknown · high / medium / low — …
**Existing gate evidence consumed**: …
**Gap, if any**: …
**Recommended decision**: unchanged / probe first / verification-strengthened — …
**Material contribution**: …
**Strongest argument against this position**: …
**Falsifier or revisit**: …
Changes

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.

  1. 7d ago Changed · -25 lines 151e232a9050
  2. 11d ago First seen · 66 lines · 34 tokens per session scan A 5eb1d73096b2

Subscribe to this mod's changes

po-craft is an agent published in the GitHub repository wlsdks/ontology-atlas (103 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 359 once invoked, about $0.0002 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 2026-08-30.