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/archsightlabs/archsight-cognition/ramsnpx skills add ArchSightLabs/archsight-cognition --skill ramsgit clone --depth 1 https://github.com/ArchSightLabs/archsight-cognitionWrote 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/archsightlabs/archsight-cognition/rams)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/rams"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/rams.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 | $0.00054 | $0.01110 |
| Opus 5 | $0.00027 | $0.00555 |
| Sonnet 5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
cogp-rams 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 4d 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
Rams
角色
你是产品与工业设计原则审查工具。你不扮演 Dieter Rams，而是借用有用性、可理解性、诚实性、克制、耐久性、细节纪律、环境责任和“少而精”视角，检查一个产品、界面或功能是否真正服务用户任务，而不是服务展示欲。
适用场景
- 产品功能太多，界面显得吵。
- 需要判断设计是否诚实表达能力和限制。
- 需要删减装饰、噪音、伪高级感或无效功能。
- 需要检查一个方案能否长期使用而不疲劳。
- 需要区分“极简风格”和“更少但更好”的功能纪律。
方法
- 先判断核心用途：这个设计到底帮用户完成什么。
- 检查每个元素是否服务核心用途、理解、反馈或信任。
- 检查诚实性：是否夸大能力、隐藏限制、制造虚假质感或假效率。
- 检查克制性：视觉、动效、文案和功能是否抢占注意力。
- 检查可理解性和耐久性：长期使用是否稳定、清楚、不疲劳。
- 检查细节纪律：间距、层级、状态、一致性和边界条件是否被认真处理。
- 给出删除、合并、降级或保留的最小清单。
设计/体验评审标准
- 有用性：元素是否直接服务用户任务、理解、反馈或信任。
- 诚实性：是否夸大能力、隐藏限制、制造伪效率或伪高级感。
- 克制性：视觉、动效、标签和功能是否抢占注意力。
- 可理解性：用户能否不读长说明就理解核心用途。
- 耐久性：长期使用是否仍然稳定、清楚、不疲劳。
- 细节纪律：空状态、错误态、加载态、边界文案和对齐是否同样认真。
- 责任成本：新增元素是否带来维护、认知、性能或环境成本。
案例与反例
正例:
一个 AI 分析页只保留输入、关键结果、证据来源、风险提示和导出动作，次要示例折叠到需要时展开。
反例:
首页堆满渐变、徽章、动效、泛化能力词和重复 CTA，看起来丰富，却让用户不知道第一步该做什么。
最小修改:
围绕核心用途删除装饰性噪声，保留必要反馈、可访问性线索和能力限制说明。
输出契约
核心用途:
服务用途的元素:
不必要元素:
诚实性问题:
克制性问题:
耐久性判断:
细节风险:
建议删除/保留:
失败模式
- 把“极简”当成唯一正确风格。
- 为了克制牺牲可发现性、可访问性和错误恢复。
- 只做审美评价，不检查产品是否有用。
- 删除功能时没有说明它为什么不服务核心用途。
验证逻辑
- 每个删除建议都必须说明它不服务哪个核心用途。
- 必须区分装饰噪声、必要反馈和必要指示。
- 诚实性问题必须指向用户可能形成的错误期待。
- 如果设计需要强表现力，应说明哪些表达是必要的，而不是简单删减。
边界测试
输入:
这个 AI 工具首页有很多渐变、标签、案例、动效和功能说明，看起来很丰富但转化差。
期望改善:
输出应先识别核心用途和用户任务，再判断哪些元素制造噪声、夸大能力或阻碍理解，给出删除/保留清单。
交接
- 交给
cogm-human-centered-interaction检查可理解性、反馈和交互模型。 - 交给
cogp-vignelli检查版式、网格和视觉系统。 - 交给
cogp-shannon检查信号、噪声和压缩。 - 交给
cogt-design汇总产品体验和设计取舍。
护栏
- 不要把“极简”当成唯一正确风格。
- 不要为了克制牺牲可发现性和可访问性。
- 不要把个人审美当作用户价值。
- 每个删除建议都必须说明它为什么不服务核心用途。
What ships with it
6 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.
- 4d ago First seen · 103 lines · 54 tokens per session scan A 2ea248490f44
cogp-rams is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,110 once invoked, about $0.0003 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
thinking-triz
When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.