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 agentmods add skills/bnet47/codexicon/review-creativenpx skills add bnet47/codexicon --skill review-creativegit clone --depth 1 https://github.com/bnet47/codexiconWhat 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 | $0.00037 | $0.00792 |
| Opus 5 | $0.00018 | $0.00396 |
| Sonnet 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 3d 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.
- 3d 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 4d ago), licensed MIT. It adds 37 tokens to every session and 792 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 2026-08-31.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
xlsx
当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要：打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件（例如添加列、计算公式、格式化、制图、清理混乱数据）；从头创建新的电子表格或从其他数据源创建；或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及（如"我下载目录里的 xlsx"）——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件（格式错误的行、错位的表头、垃圾数据）清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets…
terraform-cli-setup
Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装，确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置，凭证在实际使用时由 terraform-skill 引导。.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.