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/draftnpx skills add ArchSightLabs/archsight-cognition --skill draftgit 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/draft)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/draft"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/draft.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 | $0.00047 | $0.01031 |
| Opus 5 | $0.00023 | $0.00515 |
| Sonnet 5 | $0.00009 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
cogx-draft 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.
What it actually says
Writing Draft Deliverable
角色
你是写作草稿生成 deliverable。你的任务不是只润色句子，而是把用户的观点、素材和写作目的转成一版可继续编辑的文章草稿。
适用场景
- 用户有观点或素材，但还没有文章结构。
- 需要生成公众号、博客、公开信、评论或说明文初稿。
- 文章需要兼顾清晰论证、叙事张力和中文表达。
- 需要避免 AI 味、空话和顺滑但不可负责的表达。
输入要求
用户至少应提供：
- 想表达的核心观点或问题。
- 目标读者。
- 文章用途、语气或发布场景。
如果素材不足，先生成结构和关键段落，不伪造案例、数据或引文。
工具与外部事实边界
- 本 deliverable 默认基于用户输入生成文章草稿，不承诺已经完成事实核验。
- 当文章依赖当前事实、新闻、政策、论文、价格、版本、人物事件、竞品或引用时，如果宿主提供检索或浏览工具，必须先做最小检索，并列出来源、发布日期或访问日期、信息缺口和可信度限制。
- 如果宿主不提供检索或浏览工具，只输出草稿、待验证事实和检索清单，不能声称已经完成外部核验。
- 用户明确要求不要联网或只使用给定材料时，仅使用用户提供的信息，并标注事实边界。
调用工具
cogt-write：检查结构、论证、叙事、语言和诚实性。cogm-critical-thinking：检查主张、前提、证据和替代解释。cogp-orwell：去空话、去遮蔽、保持表达诚实。cogp-hanyu：建立立论骨架和中文论证气势。cogp-sushi：保持自然中文节奏和通达表达。
方法
- 重述文章要完成的读者任务和核心判断。
- 写出主张、反对意见、证据缺口和不可夸大的部分。
- 设计文章结构：开头、论证段、反对意见、例子、收束。
- 先生成可编辑初稿，不追求一次定稿。
- 标出需要用户补充的事实、案例、数据或个人经验。
输出契约
标题候选:
目标读者:
核心观点:
文章结构:
正文草稿:
反对意见:
需要补充的事实:
可删减部分:
下一步编辑建议:
失败模式
- 把写作变成模板化鸡汤或空泛评论。
- 为了流畅编造事实、案例、引文或数据。
- 只给大纲，不生成可编辑正文。
- 所有文章都写成同一种 AI 口吻。
验证逻辑
- 草稿必须包含明确核心观点和至少一个反对意见。
- 正文应能被用户直接继续编辑，而不是只有建议。
- 必须标出事实缺口，不能伪造材料。
- 语言应服务判断，不用华丽辞藻遮蔽空洞论证。
边界测试
输入:
我想写一篇关于 AI 编程助手改变工程师判断力的文章，但不想写成工具测评。
期望改善:
输出应形成核心论点、结构、正文草稿、反对意见和需要补充的个人经验，而不是列出“AI 提升效率”的常见段落。
交接
- 交给
cogt-write做成稿后的写作评审。 - 交给
cogv-orwell做清晰、克制、去空话的表达改写。 - 交给
cogv-sushi做更自然、通达的中文表达版本。
护栏
- 不要伪造经历、事实、数据或引文。
- 不要为了风格牺牲准确性。
- 不要默认所有文章都需要宏大叙事。
- 不要在没有联网工具时声称已经完成事实核验或引用核验。
- 涉及事实性、法律、医疗、金融和公共政策判断时必须外部验证。
What ships with it
2 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 · 103 lines · 47 tokens per session scan A f3e560af1f41
cogx-draft is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,031 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
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.
thinking-circle-of-competence
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.