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 instructions/archsightlabs/archsight-cognition/agents-mdgit 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/instructions/archsightlabs/archsight-cognition/agents-md)<a href="https://agentmods.dev/instructions/archsightlabs/archsight-cognition/agents-md"><img src="https://agentmods.dev/badge/instructions/archsightlabs/archsight-cognition/agents-md.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 | $0.01007 | $0.01007 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
archsight-cognition AGENTS.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件供 Codex（OpenAI Codex / codex.ai） 在本仓库中工作时参考。 本文件是 Codex 的工具入口适配器，不复制公共规范正文。
必读入口
开始任何工作前，先阅读：
Codex 特别说明
- Codex 在执行终端命令时，须优先使用项目根目录的
Makefile或scripts/中的辅助脚本（如存在）。 - Codex 在用户指定或任务适合本仓库技能包时，须先阅读 Personas、Methods、对应
personas/*/*/SKILL.md、methods/*/SKILL.md、teams/*/SKILL.md或deliverables/*/SKILL.md。 - 生成代码时，严格遵守
AI_CODING_RULES.md第二节「AI 行为准则」，尤其是最小代码和不做假设原则。 - Codex 不得在未经验证的状态下关闭 PR 或标记任务为完成。
ArchSight Cognition
当任务需要问题澄清、写作评审、研究设计、战略判断或跨学科决策复盘时， 从本仓库加载最相关的认知工具。
默认路由：
- 需求和概念不清：
personas/philosophy/socrates/SKILL.md - 不确定性和证据判断：
personas/mathematics/bayes/SKILL.md - 变量、约束和系统建模：
personas/physics/newton/SKILL.md - 不知道该用哪个工具：
teams/thinking-council/SKILL.md - 高风险决策：
teams/decision-council/SKILL.md - 长期议题、立场压力测试和结构化分歧：
debates/README.md或debates/<topic>/SKILL.md - 文章、叙事和表达：
teams/writing-review/SKILL.md - 产品、体验、视觉和交互：
teams/design-review/SKILL.md - 产品战略、定位和最小验证：
teams/product/SKILL.md - 技术领导、研发组织和交付反馈：
teams/lead/SKILL.md - 教育、学习路径和亲子成长：
teams/learning-path/SKILL.md - 需要生成明确产物：
deliverables/README.md或deliverables/<task>/SKILL.md
综合 team 工具统一使用短命令，例如 cogt-think、cogt-decide、cogt-write、cogt-design、cogt-learn。
生成型交付物统一使用 cogx- 前缀，例如 cogx-prd、cogx-decision-memo、cogx-draft、cogx-research-brief。
单个 persona 工具统一使用 cogp- 前缀，例如 cogp-socrates、cogp-bayes、cogp-newton。
方法工具统一使用 cogm- 前缀，例如 cogm-critical-thinking、cogm-structured-problem-solving、cogm-first-principles。
风格化口吻工具统一使用 cogv- 前缀，例如 cogv-kant、cogv-nietzsche。cogv-* 只用于口吻和表达风格，不声称历史人物本人在说话。
结构化分歧和长期议题工具统一使用 cogd- 前缀，例如 cogd-general、cogd-life、cogd-technology。
不要人格 cosplay。把 persona 当作学科思维工具，而不是历史人物模拟。
persona 和 voice 只使用已离世人物或稳定历史传统；仍在世人物、活跃企业家和个人品牌材料只能去人物中心化后进入 methods/ 或 team 参考材料。
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.
- 4d ago First seen · 57 lines · 1,007 tokens per session scan A f3357a441e24
archsight-cognition AGENTS.md is an instructions file published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,007 tokens to every session, about $0.0050 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 instructions, from other repositories
cc-thinking-skills CLAUDE.md
Instructions for tjboudreaux/cc-thinking-skills: Follow AGENTS.md for repository workflow.
cc-thinking-skills AGENTS.md
Instructions for tjboudreaux/cc-thinking-skills, covering agent guidelines, first principles, skill authoring & eval standards, default workflow and verification.
anvil CLAUDE.md
Claude Code instructions for mulkatz/anvil, covering anvil — adversarial thinking plugin, what this is, architecture, key files and documentation.
notfair-plugin AGENTS.md
AGENTS.md instructions for nowork-studio/notfair-plugin, covering notfair — skill resolver for ai agents, how to use this file, seo, paid ads and analytics.
domscribe CLAUDE.md
Instructions for patchorbit/domscribe, covering claude.md, what is domscribe?, how to work on this codebase, commands and install dependencies (pnpm, not npm).
adeu GEMINI.md
Gemini CLI instructions for dealfluence/adeu, covering adeu — native track changes for ai, available tools, readdocx, processdocumentbatch and applytextrevision.