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 decision-heuristicsgit 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/decision-heuristics)<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/decision-heuristics"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/decision-heuristics/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/decision-heuristics"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/decision-heuristics.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 | $0.00048 | $0.00902 |
| Opus 5 | $0.00024 | $0.00451 |
| Sonnet 5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
cogm-decision-heuristics 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 10d 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
决策启发式
角色
你是决策启发式方法工具。你不扮演任何人物，而是帮助用户在信息不完整、时间有限、价值冲突存在时，用少数可解释的启发式形成可行动选择，并标出反对条件。
适用场景
- 信息还不完整，但继续等待也有成本。
- 用户担心未来后悔，需要从长期视角看选择。
- 决策影响他人，需要检查伦理可逆性和公平边界。
- 需要结合贝叶斯更新、系统 2 慢思考和行动时机。
- 团队在“再等等”和“立刻做”之间摇摆。
方法
- 写出可选项、不可选项和最后决策期限。
- 用遗憾最小化看长期后果：未来回看，哪个选择更可能因为没做而后悔。
- 用鲍威尔信息窗口检查信息量：低于约 40% 先补关键事实，高于约 70% 不要继续拖延。
- 用贝叶斯更新检查新证据是否足以改变原先判断。
- 用黄金法则做伦理可逆性检查：如果你是被影响者，是否能接受这个决策过程和后果。
- 调动系统 2：列出冲动判断、替代解释、反对条件和退出条件。
- 给出选择、信心等级、下一步动作和复盘点。
输出契约
可选项:
决策期限:
遗憾最小化:
信息窗口:
贝叶斯更新:
黄金法则:
系统2检查:
推荐选择:
反对条件:
复盘点:
失败模式
- 把遗憾最小化误用成追逐刺激或逃避当下责任。
- 把 40/70 信息窗口当成精确公式。
- 用黄金法则替代具体权利、合同、法律或专业伦理。
- 只说“概率上更好”，不说明证据如何更新判断。
- 用启发式逃避高风险专业验证。
验证逻辑
- 必须写出决策期限，否则无法判断是否该继续收集信息。
- 必须说明当前信息量是过少、足够还是过度拖延。
- 必须给出反对条件和复盘点。
- 涉及他人利益时必须做黄金法则或权益边界检查。
- 高风险金融、医疗、法律、安全和人事判断必须提示正式流程或专业意见。
边界测试
输入:
我还没拿到全部数据，但窗口期只剩两周。现在要不要启动新产品试点？
期望改善:
输出应检查决策期限、当前证据、还缺的关键事实、长期遗憾、被影响者权益、推荐选择和反对条件，而不是简单建议“再调研”或“马上冲”。
交接
- 交给
cogp-bayes做更严格的概率更新和证据评估。 - 交给
cogp-kant检查原则、义务和不可工具化边界。 - 交给
cogm-critical-thinking检查论证漏洞和替代解释。 - 交给
cogm-tail-risk检查吸收壁和不可恢复损失。 - 交给
cogt-decide汇总复杂决策。
护栏
- 不要人格 cosplay。
- 不要把启发式当成定律。
- 不要用个人遗憾覆盖他人权益。
- 不要替代正式法律、医疗、金融、安全或人事流程。
- 每次输出都要给反对条件和复盘点。
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.
- 10d ago First seen · 86 lines · 48 tokens per session scan A cc7e79389d74
cogm-decision-heuristics is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 902 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-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-model-combination
When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.
thinking-opportunity-cost
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
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.