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 bnet47/codexicon --skill review-creativegit clone --depth 1 https://github.com/bnet47/codexiconWrote 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/bnet47/codexicon/review-creative)<a href="https://agentmods.dev/skills/bnet47/codexicon/review-creative"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/review-creative/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/bnet47/codexicon/review-creative"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/review-creative.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 | $0.00037 | $0.00792 |
| Opus 5.5 | $0.00015 | $0.00317 |
| Sonnet 5.5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
review-creative 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review creative work
Review evidence, not personal taste. Identify customer-facing weaknesses that reduce comprehension, trust, usability, distinctiveness, or conversion. Do not modify files.
1. Establish the review contract
Read the request or brief, audience, primary task or action, product and brand constraints, source material, and artifact under review. Establish whether the surface is brand or product, because expressive marketing and repeated-use product UI require different judgments.
Build an evidence packet from what is available:
- approved brief and acceptance conditions;
- running or rendered artifact at representative sizes;
- relevant source, tokens, and interaction behavior;
- factual sources, claim approvals, customer evidence, and channel rules;
- baseline or earlier version when the request claims improvement.
State missing context that limits the review. Do not invent a brand strategy and criticize the work for not following it.
Read only the applicable sections of references/review-rubric.md.
2. Run deterministic and functional checks
For interface source, run the bundled scanner when Python is available:
python .agents/skills/review-creative/scripts/scan_interface.py <files-or-directories>
Treat its output as investigation leads, not verdicts. Confirm each finding in context and ignore justified patterns. Also run the project's real lint, accessibility, performance, and browser checks when they exist and are within scope.
Inspect the primary flow and key states at representative mobile and desktop sizes. Check keyboard behavior, focus, zoom, reduced motion, loading, empty, error, success, stale data, and recovery. Render documents, decks, images, and other visual artifacts through their specialist workflow; source files alone are not visual proof.
3. Run two independent review passes
Pass A: comprehension, operation, and truth
Check whether the audience can understand the offer or task, complete it, recover from failure, and trust the result. Verify behavior, accessibility, claims, proof, links, terms, platform constraints, approvals, and data integrity.
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.
- 1mo ago First seen · 81 lines · 37 tokens per session scan A 08d1434cc2fe
review-creative is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 792 once invoked, about $0.0001 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.
Other skills, from other repositories
visual-asset-design
A guide for turning character, scene, and prop ideas into prompts for generating consistent reference images. It covers layouts, camera views, visual identity, and continuity across image variations.
ui-mockup
Create UI mockups at three fidelity levels — ASCII wireframes for quick iteration, standalone HTML mockups for delivery with requirements, and live prototypes for interaction testing.
oma-design
Define or review a visual system, DESIGN.md, or redesign direction. Use for typography, layout, color, motion, and interaction design decisions.
conversion-review
Review a landing page or form to find why visitors do not sign up or buy: unclear message, friction, missing proof, weak call to action. Looks at the real page on desktop and phone and ranks the fixes.
frontend-design
Give a web page or app its own look instead of a generic AI-made one: choose colors, type and layout on purpose before building, then critique the result. Use when building a new interface or reshaping an existing one.
brand-assets
Make images, covers and transparent cutouts that look like one family: a pinned style sheet, fixed formats, every file checked against it, and cutouts confirmed truly transparent.