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/ferroxlabs/wayland/ai-evaluation-patternsnpx skills add FerroxLabs/wayland --skill ai-evaluation-patternsgit clone --depth 1 https://github.com/FerroxLabs/waylandWrote 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/ferroxlabs/wayland/ai-evaluation-patterns)<a href="https://agentmods.dev/skills/ferroxlabs/wayland/ai-evaluation-patterns"><img src="https://agentmods.dev/badge/skills/ferroxlabs/wayland/ai-evaluation-patterns.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.08226 |
| Opus 5 | $0.00043 | $0.04113 |
| Sonnet 5 | $0.00017 | $0.01645 |
| Haiku 4.5 | $0.00009 | $0.00823 |
Grade A, and why
ai-evaluation-patterns 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 yesterday.
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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- yesterday First seen · 576 lines · 86 tokens per session scan A 8082fe549611
ai-evaluation-patterns is a skill published in the GitHub repository FerroxLabs/wayland (598 stars, last pushed today), licensed AGPL-3.0. It adds 86 tokens to every session and 8,226 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
release
Use when the maintainer wants to cut, prepare, or ship a code-by-wire release — e.g. says "bump version", "bump vX.Y.Z", "release it", "ship it", or "cut a release" — whether before the release (preparing the version bump and the changelog PR) or after the bump PR has merged (tagging and publishing).
feishu-create-doc
创建飞书云文档。从 Lark-flavored Markdown 内容创建新的飞书云文档，支持指定创建位置（文件夹/知识库/知识空间）。.
ordinus-ui-system
Build Ordinus renderer UI in the intended product style. Use when changing React UI, layout, Tailwind styling, shadcn-style components, status panels, navigation, empty states, forms, tables, task views, or user-facing product text.
feishu-troubleshoot
飞书插件问题排查工具。包含常见问题 FAQ 和深度诊断命令（/feishudoctor）。 常见问题可随时查阅。诊断命令用于排查复杂问题（多次授权仍失败、自动授权无法解决等）， 会检查账户配置、API 连通性、应用权限、用户授权状态，并生成详细的诊断报告和解决方案。.
ipc-contract-design
Design and maintain Ordinus typed IPC contracts. Use when adding or changing window.ordinus APIs, ipcMain handlers, ipc channel names, shared request/response types, Zod schemas, preload bridge methods, or renderer calls into main process.
sqlite-minimal-persistence
Extend Ordinus SQLite persistence conservatively. Use when touching better-sqlite3, Drizzle schema, database bootstrap, appmeta, migrations, durable state, persistence boundaries, or proposals to add new product tables.