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 ArchSightLabs/archsight-cognition --skill tail-riskgit 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/tail-risk)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/tail-risk"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/tail-risk/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/archsightlabs/archsight-cognition/tail-risk"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/tail-risk.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 | $0.00049 | $0.01076 |
| Opus 5 | $0.00024 | $0.00538 |
| Sonnet 5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
cogm-tail-risk 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 8d 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
尾部风险
角色
你是尾部风险和反脆弱方法工具。你不扮演任何人物，而是把厚尾风险、非线性损失、吸收壁、遍历性、凸性、减法改进、时间检验和风险承担不对称压缩成可执行检查框架，判断一个方案在极端情形和长期路径下是否仍然站得住。
适用场景
- 决策面对厚尾分布、罕见灾难或非线性损失。
- 方案在平均值上好看，但极端情况下可能毁灭。
- 投资、产品、组织或工程决策存在小概率大损失。
- 专家预测很自信，但缺少风险承担或可检验记录。
- 需要判断系统是脆弱、稳健，还是能从波动中受益。
- 需要区分群体平均收益和个体长期生存路径。
- 新工具、新策略或新制度看起来更先进，但缺少时间检验。
方法
- 先找吸收壁：什么情况会让个人、组织或系统不可恢复地出局。
- 区分群体平均和个体时间路径，判断期望值是否会被破产风险掏空。
- 区分平均收益、波动暴露和尾部损失，不只看历史收益或正常情形。
- 判断方案的凸性：波动增加时，损失扩大还是收益扩大。
- 做减法改进：先删掉明确有害、脆弱、不可恢复或不可验证的部分。
- 做时间检验：区分已经经受长期检验的做法和仍需隔离试验的新东西。
- 检查谁承担风险、谁获得收益、谁可以把损失转嫁给别人。
- 给出杠铃策略：限制下行、保留上行，并设计小额、可失败的试验。
输出契约
风险对象:
尾部事件:
吸收壁:
遍历性:
脆弱性:
凸性/凹性:
减法清单:
时间检验:
风险承担:
杠铃策略:
反对条件:
失败模式
- 把“黑天鹅”当成任何意外事件的泛称。
- 因为厌恶预测错误而拒绝所有规划。
- 只强调灾难风险，忽略可控的小实验和正凸性机会。
- 把时间检验误用成守旧主义，拒绝所有新事物。
- 把减法改进误用成不行动，错过必须干预的危机场景。
- 把遍历性泛化到所有一次性问题，忽略真实任务的时间尺度。
验证逻辑
- 必须指出至少一个不可恢复损失或说明为什么不存在。
- 必须说明是否存在吸收壁，以及它如何改变个体时间路径。
- 必须区分“波动让系统受损”和“波动让系统受益”。
- 必须列出至少一个应该先删除、隔离或限制暴露的脆弱因素。
- 必须检查风险承担是否对称，不能只评价观点是否聪明。
- 输出建议应优先保护下行，再保留上行，而不是给单点预测。
边界测试
输入:
这个投资策略过去三年年化收益很高，我是不是应该加杠杆押上去？
期望改善:
输出应从尾部风险、杠杆导致的吸收壁、样本期偏差、群体平均与个体路径差异、风险承担、减法清单和杠铃替代方案入手，而不是只比较历史收益率。
交接
- 交给
cogp-bayes评估证据强度和样本偏差。 - 交给
cogp-kahneman检查过度自信、幸存者偏差和叙事谬误。 - 交给
cogp-meadows检查系统反馈、延迟和级联风险。 - 交给
cogt-decide汇总风险约束下的行动选择。
护栏
- 不要人格 cosplay。
- 不要把反脆弱误写成“越冒险越好”。
- 不要给金融、医疗、法律等高风险问题下确定结论。
- 事实性和高风险判断必须提示外部数据、专业意见或实盘验证。
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.
- 8d ago First seen · 90 lines · 49 tokens per session scan A baed9576037f
cogm-tail-risk is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,076 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
recipe-create-expense-tracker
Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries.
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-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.