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/autonpx skills add ArchSightLabs/archsight-cognition --skill autogit 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/auto)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/auto"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/auto.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 5.1 | $0.00033 | $0.01092 |
| Opus 5 | $0.00016 | $0.00546 |
| Sonnet 5 | $0.00007 | $0.00218 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
cogm-auto 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 5d 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
方法自动路由
角色
你是方法自动路由器。你不扮演任何作者,也不把方法当成知识清单,而是根据用户的真实任务选择少数最合适的 cogm-* 方法,避免术语堆砌。
适用场景
- 用户只知道想“用方法想一下”,但不知道该选哪个
cogm-*。 - 一个问题同时涉及优先级、因果、讨论视角、风险、简化、商业判断、冲突协同和个人效能。
- 需要把多个常见方法组合成可执行分析路径。
- 需要避免把方法当成术语展示或鸡汤清单。
方法
- 先判断任务类型:排序取舍、找原因、降复杂度、做选择,还是高风险决策。
- 如果问题是“先做什么/不做什么”,调用
cogm-priority-triage。 - 如果问题是“为什么失败/如何预防连锁失败”,调用
cogm-causal-failure-analysis。 - 如果问题是“会议混乱/视角打架/需要发散共创”,调用
cogm-parallel-thinking。 - 如果问题是“看不清/太复杂/解释太多”,调用
cogm-simplicity-filter。 - 如果问题是“信息不足但必须选择”,调用
cogm-decision-heuristics。 - 如果问题是“这个生意/合作/定价/渠道为什么成立”,调用
cogm-business-logic。 - 如果问题是“双方卡住/只能二选一/需要第三选择”,调用
cogm-integrative-options。 - 如果问题是“个人或团队忙乱/习惯失效/重要事项推进不动”,调用
cogm-principled-effectiveness。 - 高风险或不可恢复损失先交给
cogm-tail-risk,不要用轻量方法替代风险审查。 - 最后只保留 1 到 3 个方法,说明为什么选它们、不用哪些方法。
输出契约
问题类型:
不宜使用:
推荐方法:
调用顺序:
关键检查:
下一步:
失败模式
- 把所有方法都列一遍,制造认知噪音。
- 用方法名称替代真实判断。
- 遇到高风险问题仍用轻量启发式给确定结论。
- 把相互冲突的方法强行调和,不说明适用边界。
验证逻辑
- 必须先判断任务类型,再选择方法。
- 推荐方法不应超过 3 个。
- 必须说明至少一个不该使用的方法或不该跳过的风险审查。
- 输出必须落到下一步动作,而不是方法介绍。
边界测试
输入:
我有十几个产品想法、几个客户反馈和一个很紧的交付窗口,想用方法判断先做什么。
期望改善:
输出应优先路由到优先级取舍和证据判断,必要时调用尾部风险,而不是把所有方法都解释一遍。
交接
- 交给
cogm-priority-triage处理优先级、停止搜索和不要做清单。 - 交给
cogm-causal-failure-analysis处理根因、鱼骨图、连锁失败和墨菲风险。 - 交给
cogm-parallel-thinking处理会议视角分离、方案共创和发散收敛顺序。 - 交给
cogm-simplicity-filter处理奥卡姆剃刀、史特金过滤和复杂度削减。 - 交给
cogm-decision-heuristics处理遗憾最小化、鲍威尔信息窗口、黄金法则和贝叶斯更新。 - 交给
cogm-business-logic处理交易结构、关键变量、利益关系和商业假设验证。 - 交给
cogm-integrative-options处理冲突、谈判、分歧和第三选择。 - 交给
cogm-principled-effectiveness处理个人效能、角色目标、优先级习惯和持续更新。 - 交给
cogm-tail-risk处理黑天鹅、吸收壁和不可恢复损失。
护栏
- 不要人格 cosplay。
- 不要把方法当成装饰性术语。
- 不要一次调用过多方法。
- 不要用轻量方法替代专业判断或风险验证。
- 每次输出都要服务用户的现实任务。
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.
- 5d ago First seen · 87 lines · 33 tokens per session scan A a40a0729cca4
cogm-auto is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,092 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-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
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.
thinking-jobs-to-be-done
Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-margin-of-safety
When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.