Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.
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 EverMind-AI/Raven --skill review-against-ai-patternsgit clone --depth 1 https://github.com/EverMind-AI/RavenWrote 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/evermind-ai/raven/review-against-ai-patterns)<a href="https://agentmods.dev/skills/evermind-ai/raven/review-against-ai-patterns"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/review-against-ai-patterns/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/evermind-ai/raven/review-against-ai-patterns"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/review-against-ai-patterns.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 | $0.00102 | $0.00906 |
| Opus 5.5 | $0.00041 | $0.00362 |
| Sonnet 5.5 | $0.00020 | $0.00181 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
review-against-ai-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 29d 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.
What it actually says
反 AI 模式审查
本 Skill 集中保管反模式图鉴、ANTI-SLOP-CHECK.md 合同与反模板渲染审查，从
$visual-artifact-design 与 $build-polished-visual-frontends 无损迁出；领域 Skill 保留各自的停下
信号与返工测试。
1. 方向决定之前，完成图鉴对照（强制，适用于一切视觉产物任务）
- 风险路由：读取
references/anti-slop-gallery/page-1.jpg的索引，按任务、参考路线与代表画面 的实际风险选出相关组，再读取覆盖这些组的 2–4 页标本；若方向无法归类或多个高风险组跨页， 继续读取直至风险得到覆盖。不要为凑页数增加无关阅读。 - 在运行时提供的当前工作目录中，以相对路径
ANTI-SLOP-CHECK.md建立账本，与产物同为交付的一部分； 条目按账本格式写。当前工作目录是本会话的根目录；账本、计划和辅助文件 都保存在这里，不要向上寻找共享的项目根目录。成品若放在子目录中，账本仍留在当前工作目录。
ANTI-SLOP-CHECK.md——负面：避什么。只记录路由到的高／中风险组、当前可见症状、对应标本、
正向标杆机制、修改和重渲染证据；低风险与不涉及项不写空章节。交付前再对完整产物做一次全局扫描，
新出现的风险补入账本。遗漏实际命中的组即未完成，文档篇幅和逐组表态不构成质量证据。
2. 制作中
制作中任一图鉴组在产物里成形——G 灰色小字、N 数字卡、P 配色模板、B 表达块、H 待补占位、
T 胶囊堆、O 双语眉题、S 编号字诀、W 模板文案、D 插画画风——立即停下重构，并更新
ANTI-SLOP-CHECK.md 对应组。判断单个元素是否命中时，读取
反模板渲染审查，并单独查看图鉴对应页。
3. 检查与交付
审查门槛、证据组、分项观察、常见症状与修复、高影响问题协议与通过条件见 反模板渲染审查。
是否调用独立 reviewer、何时复审和是否继续修改，由模型根据风险和 reviewer 结果判断；Runner
只提供工具、日志和用户明确设置的调用上限，不裁决审美阶段。给 reviewer 的输入只包含用户原始
请求、可查看参考、必要对象语义和当前渲染画面，不附加模型理由或自我评分。没有独立 reviewer
时完成隔离自检，并将结果标为 SELF_REVIEW_ONLY。
完成条件：ANTI-SLOP-CHECK.md 已记录路由到的高／中风险与修改证据，并在终态完成全局扫描；实际命中的
病症没有因未被预先路由而漏记，文档与当前像素一致。
What ships with it
17 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.
- agents/openai.yaml 383 B
- references/anti-slop-gallery/page-1.jpg 213 KB
- references/anti-slop-gallery/page-10.jpg 185 KB
- references/anti-slop-gallery/page-11.jpg 228 KB
- references/anti-slop-gallery/page-12.jpg 173 KB
- references/anti-slop-gallery/page-13.jpg 144 KB
- references/anti-slop-gallery/page-14.jpg 200 KB
- references/anti-slop-gallery/page-2.jpg 229 KB
- references/anti-slop-gallery/page-3.jpg 253 KB
- references/anti-slop-gallery/page-4.jpg 168 KB
- references/anti-slop-gallery/page-5.jpg 258 KB
- references/anti-slop-gallery/page-6.jpg 230 KB
- references/anti-slop-gallery/page-7.jpg 303 KB
- references/anti-slop-gallery/page-8.jpg 224 KB
- references/anti-slop-gallery/page-9.jpg 216 KB
- references/anti-slop-review.md 21 KB
- references/ledger-format.md 1.3 KB
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.
- 29d ago Changed · +1 lines 789fa7320722
- 1mo ago First seen · 44 lines · 102 tokens per session scan A 7159c3f7ffc8
review-against-ai-patterns is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 906 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
anatomy
Explain an idea as an interactive isometric machine figure.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
ip-as-logo
Design minimal cute IP mascot marks readable at 32px.
tldraw-offline
Drive and script tldraw offline canvases with an agent.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.