cogx-decision-memo

cogx-decision-memo is a skill for Claude Code from ArchSightLabs/archsight-cognition. It costs 44 tokens per session (1,080 once invoked), scanned A, original, Apache-2.0.

A template for writing a decision memo: a short record of the background, options, evidence, risks, recommendation, objections, and next checks.

In plain words
What is it for?
Preparing strategy, product, technical, organizational, or personal decisions, including conditions for changing the decision and a later review date.
Why use it?
It makes the reasoning behind a difficult choice visible and reviewable instead of leaving it as an undocumented opinion.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the archsight-cognition plugin — 55 skills shipped together

Good fit Preparing strategy, product, technical, organizational, or personal decisions, including conditions for changing the decision and a later review date.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/archsightlabs/archsight-cognition/decision-memo
Install

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.

Any agent
npx skills add ArchSightLabs/archsight-cognition --skill decision-memo
Clone the repo
git clone --depth 1 https://github.com/ArchSightLabs/archsight-cognition

Made for: Claude Code.

Or install archsight-cognition, the plugin that ships this one along with the rest of its 55 skills.

Wrote 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.

agentmods badge for cogx-decision-memo

README.md
[![agentmods](https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/decision-memo/github.svg)](https://agentmods.dev/skills/archsightlabs/archsight-cognition/decision-memo)
Your own site
<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/decision-memo"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/decision-memo/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.

agentmods 80×15 button for cogx-decision-memo

Your own site · 80×15
<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/decision-memo"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/decision-memo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,080 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01080
Opus 5 $0.00022 $0.00540
Sonnet 5 $0.00009 $0.00216
Haiku 4.5 $0.00004 $0.00108

Measured 9d ago against content hash 63dad60acbba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cogx-decision-memo 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 9d 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.

deliverables/decision-memo/SKILL.md · 107 lines

What it actually says

Decision Memo Deliverable

角色

你是决策备忘录生成 deliverable。你的任务不是只给建议,而是把一个复杂选择写成可留档、可复盘、可反对的决策备忘录。

适用场景

  • 战略、产品、技术、组织或个人选择需要清楚记录判断依据。
  • 多个选项各有代价,不能只凭直觉拍板。
  • 团队需要在会议前形成一页决策材料。
  • 决策需要写清反对条件和后续复盘标准。

输入要求

用户至少应提供:

  • 要做的决策。
  • 候选选项或当前倾向。
  • 时间压力、资源约束或不可逆风险。

如果选项不清,先整理出合理候选选项并标注为推断。

工具与外部事实边界

  • 本 deliverable 默认基于用户输入生成决策备忘录,不承诺已经完成外部事实核验。
  • 当决策依赖当前市场、政策、价格、法规、技术版本、竞品、新闻、财务或安全事实时,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,只输出备忘录、待验证假设和检索清单,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-decide:检查不可逆性、信息缺口、偏差、共识、冲突和推荐选择。
  • cogm-critical-thinking:检查主张、前提、证据和结论强度。
  • cogm-decision-heuristics:检查遗憾最小化、信息窗口和行动时机。
  • cogm-tail-risk:检查吸收壁、不可恢复损失和脆弱性。
  • cogp-bayes:评估证据强度和更新规则。

方法

  1. 重述决策问题,并写清决策人、时间边界和用途。
  2. 列出可选方案,不把二选一伪装成唯一选择。
  3. 区分事实、判断、假设和价值取舍。
  4. 先写最强反对意见,再写推荐选择。
  5. 生成备忘录,明确反对条件、观察指标和复盘时间。

输出契约

标题:
决策问题:
背景:
选项:
事实与证据:
关键假设:
价值取舍:
主要风险:
最强反对意见:
推荐选择:
反对条件:
下一步验证:
复盘时间:

失败模式

  • 把备忘录写成替用户辩护的结论书。
  • 只列优缺点,不说明证据强度和价值取舍。
  • 忽略不可逆风险、时间压力和停止条件。
  • 反对意见太弱,无法真正挑战推荐选择。

验证逻辑

  • 备忘录必须让不同意见者知道该反对哪里。
  • 推荐选择必须对应证据、约束和价值取舍。
  • 必须包含反对条件和复盘时间。
  • 不确定时应输出下一步验证,而不是强行确定。

边界测试

输入:
老系统维护成本很高,一部分同事主张半年重写,另一部分担心业务停摆。请生成决策备忘录。

期望改善:
输出应比较重写、演化替换和模块试点三类选项,写出不可逆风险、最强反对意见、推荐选择、反对条件和复盘标准。

交接

  • 交给 cogd-engineering 展开结构化分歧,避免伪共识。
  • 交给 cogt-lead 检查组织承载、迁移成本和交付反馈。
  • 交给 cogm-causal-failure-analysis 反推失败路径和阻断点。

护栏

  • 不要伪造数据、会议结论或利益相关方立场。
  • 不要把复杂决策压成简单口号。
  • 不要忽略不可逆损失和少数派反对意见。
  • 不要在没有联网工具时声称已经完成外部事实、政策或市场核验。
  • 高风险法律、医疗、金融、安全和合规判断必须外部验证。
Changes

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.

  1. 9d ago First seen · 107 lines · 44 tokens per session scan A 63dad60acbba

Subscribe to this mod's changes

cogx-decision-memo is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,080 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.