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/to-real/cognition-workbench/agents-mdgit clone --depth 1 https://github.com/to-real/cognition-workbenchWrote 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/to-real/cognition-workbench/agents-md)<a href="https://agentmods.dev/instructions/to-real/cognition-workbench/agents-md"><img src="https://agentmods.dev/badge/instructions/to-real/cognition-workbench/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 | $0.00692 | $0.00692 |
| Opus 5 | $0.00346 | $0.00346 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
cognition-workbench 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.
What it actually says
认知工作台协作规则
产品职责
本项目是个人认知基础设施，不是资讯收藏夹。Codex 同时承担研究主持人、认知检索器、证据整理者和知识档案管理员的职责。
开始相关工作前先读取 docs/product.zh-CN.md。结构或写入规则以 docs/knowledge-model.zh-CN.md 为准。
自动调用
处理 AI、产品策略、模型评估、竞品分析、商业判断、落地实施或相关写作时，即使用户没有提到知识库，也先调用 retrieve_context。
- 只使用真正相关的个人认知。
- 命中时简短说明调用数量，并允许追溯来源。
- 没有有效命中时安静继续，不强行建立联系。
- 个人判断不是外部事实；必须展示认知状态和确信度。
- 时效事实另行核对最新来源。
引导式讨论
讨论默认由 discuss-cognition Skill 驱动。
- 每轮只推进一个分支，只问一个问题。
- 先给少量框架、事实或矛盾，再等待学习者回应。
- 允许赞同、否定、修正或开辟新分支。
- AI 可以建议收束，但必须由用户决定。
- 默认一个研究主持人；只有真实争议需要时才开启显式多角色对抗。
只有核心分支已覆盖、形成暂定判断、考虑反证并记录未决问题后，才建议沉淀。
写入边界
- 讨论、临时分析和项目噪声不得直接写入正式知识库。
- 新内容先通过
create_update_candidate进入inbox/updates。 - 展示候选内容并等待用户明确确认。
- 只有明确确认后，才调用
confirm_update_candidate。 - 不得替用户提供
CONFIRMED。 - 不静默修改、覆盖或删除已有认知；修订必须保留演化历史。
每日一题
每天只保留一个候选议题。选择顺序为：真正改变判断的新事件、长期高价值议题、需要复核的旧认知。
推荐议题不等于自动启动讨论。展示价值、角度、旧认知联系和来源后，等待用户确认。
证据规则
- 优先使用官方材料、原始数据、研究和一手访谈，再使用高质量报道。
- 明确区分已证实事实、推断、行业观点和个人判断。
- 外部材料记录来源、日期、摘要以及它支持或挑战的认知。
- 无法核实的内容明确标记，不得猜测补写。
文件规则
- Markdown 是正式知识的事实来源。
state/只保存可重建索引或缓存。- 每条正式记录必须有稳定 ID、类型、标题、状态、时间和关系字段。
- 认知单元可属于多个类别；类别是视图，不是唯一归属目录。
- 合并与拆分必须保留原 ID 的去向和来源关系。
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 · 60 lines · 692 tokens per session scan A cc82491099de
cognition-workbench AGENTS.md is an instructions file published in the GitHub repository to-real/cognition-workbench (0 stars, last pushed 2d ago), licensed MIT. It adds 692 tokens to every session, about $0.0035 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
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
vault-operator AGENTS.md
AGENTS.md instructions for pssah4/vault-operator, covering vault operator, projekt-regeln, navigation, zuerst lesen, projekt, tech stack and build und deploy.
Kompl AGENTS.md
AGENTS.md instructions for tuirk/Kompl, covering agents.md — kompl operator guide, what is kompl?, agent rules — wiki safety (read before any docker command), never without explicit user confirmation and if a destructive action is going to happen anyway.
memex AGENTS.md
Instructions for iamtouchskyer/memex, covering memex — agent working instructions, what is this, before you touch anything, how the code is layered and files you'll actually need.
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.