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 lihaozheCharlie/TwhWiki --skill reasoning-lensesgit clone --depth 1 https://github.com/lihaozheCharlie/TwhWikiWrote 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/lihaozhecharlie/twhwiki/reasoning-lenses)<a href="https://agentmods.dev/skills/lihaozhecharlie/twhwiki/reasoning-lenses"><img src="https://agentmods.dev/badge/skills/lihaozhecharlie/twhwiki/reasoning-lenses/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/lihaozhecharlie/twhwiki/reasoning-lenses"><img src="https://agentmods.dev/badge/skills/lihaozhecharlie/twhwiki/reasoning-lenses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01629 |
| Opus 5 | $0.00026 | $0.00814 |
| Sonnet 5 | $0.00010 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
common-reasoning-lenses 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 12d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
通用：共享推理视角
这个 Skill 提供一组来源可核实、边界明确的人物推理视角。它不负责页面归档和模板，也不把 Wiki 写成名人观点合集。领域 Skill 决定写什么页面、保留什么结构；本 Skill 只决定在解释性判断中首先注意什么、怎样推理、什么算洞见和何时停止。
使用方式
- 用户明确要求用某个人物或多视角分析时，与
skills/consume/query/SKILL.md一起使用。 - 回信、个人主线、人生阶段、事件复盘、循环、思维模型、现实系统、城市和关系综合需要解释时，由对应领域 Skill 调用。
- 本 Skill 默认只读。写入授权、归档位置和页面模板始终由根
AGENTS.md与领域构建 Skill 决定。 - 来源索引、日期、标签、别名、实体消歧、直接引文和可观察状态分类保持中性，不使用人物视角改写。
动态发现人物
先运行：
python3 skills/common/reasoning-lenses/scripts/list_lenses.py
脚本会扫描 references/figures/ 下当前存在的全部人物文件并输出路由卡。下游 Skill 不得硬编码人物名单、数量或文件名。选择主视角后，只读取对应人物文件；需要辅助校验时再读取辅助人物文件。
新增人物只需：
- 在
references/figures/新增一份符合既有 frontmatter 与章节契约的 Markdown 文件； - 运行
python3 skills/common/reasoning-lenses/scripts/list_lenses.py --check； - 运行
python3 tools/validate_skill_system.py。
只要路由信号与推理协议完整，现有下游会自动发现并可选择新人物。
人物视角文件是独立的内容资产。由于下游采用动态发现，某个人物没有被当前样例、测试或其他文档直接点名，不代表它没有被使用或属于冗余。清理仓库时不得按静态引用次数删除人物视角；只有用户明确指定删除，或文件违反来源与协议要求且已获授权修复时，才能移除。
四档使用强度
| 强度 | 适用内容 | 规则 |
|---|---|---|
| 0：中性 | 原始证据、来源索引、元数据、日期、别名、实体事实 | 禁止使用人物视角改变事实或选择性遗漏 |
| 1：审查 | 状态追踪、人物事实、关系证据 | 只检查是否漏掉重要维度；不让人物视角成为中心结论 |
| 2：解释 | 主线、阶段、事件事后判断、循环、系统、城市、思维模型 | 1 个主视角完整推理，通常最多 1 个辅助视角做有边界校验 |
| 3：表达 | 近况回信、用户要求的解释性查询 | 主视角同时决定注意力、推理和自然表达倾向；领域 Skill 决定口吻与成品格式 |
同一来源进入不同层时可以使用不同强度和不同主视角。例如日记回信可以由雅尼完整推理，职业事件页由芒格解释机制，状态追踪仍只记录可观察变化。
共享工作流
- 建立中性证据卡，只记录事实、原句、用户解释、必要旧线索和未知。
- 运行动态发现脚本，根据当前问题而非喜好选择主视角。不能先得出通用结论再挑人物包装。
- 读取主视角文件，建立视角任务卡。
- 完整沿主视角推理，形成候选解释。
- 只有存在具体盲点时才加入辅助视角。默认最多 1 个；领域 Skill 若允许更多，每个仍必须只有一个独立任务。
- 把候选解释放回领域模板，保持事实、解释和行动的边界。
- 完成领域质量门和主视角忠实度检查。
中性证据卡
- 实际发生了什么，哪些原句和细节最有信息量？
- 用户怎样解释它？哪些是愿望、估计或尚未发生的结果？
- 哪些旧线索确实改变上下文？
- 哪些部分不知道，不能由人物视角补写？
人物视角不是证据。它可以重排注意力、提出解释和暴露盲点，但不能让一项推断升级为事实。正常摄取没有新证据时，不能只因换了人物就改写页面核心判断；用户明确授权重新解释时，保留仍成立的旧判断并说明更新范围。
视角任务卡
输出层与使用强度：
目标问题：
主视角：
选择理由：它会改变哪一项注意力或推理？
推理起点：
推理路径：
洞见标准：
停止位置：
禁止迁移：
辅助视角（如有）：
唯一任务：
允许补充：
禁止改变：
主辅关系
- 主视角决定中心关注、推理路径、洞见标准和停止位置，不是语气包。
- 辅助视角只能校验一个证据跳跃、现实边界、长期后果、情感遗漏或执行缺口。
- 辅助不能改变中心、主体结构、主要结论和结尾；若必须改变，应重新选择主视角。
- 多元性应发生在整个 Wiki，不要求每个页面同时容纳多个人物。
- 默认不在 Wiki 正文写人物姓名和名言。用户明确要求比较视角时可以展示名称，但结论仍须独立成立。
What ships with it
12 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.
- references/evidence-and-lens-guardrails.md 2.2 KB
- references/figures/albert-einstein.md 3.6 KB
- references/figures/benjamin-franklin.md 3.5 KB
- references/figures/charlie-munger.md 3.5 KB
- references/figures/elon-musk.md 3.4 KB
- references/figures/richard-feynman.md 3.4 KB
- references/figures/steve-jobs.md 3.5 KB
- references/figures/warren-buffett.md 3.5 KB
- references/figures/yanni.md 4.2 KB
- scripts/list_lenses.py 5.5 KB runs code
- tests/cross-domain-regression.md 2.1 KB
- tests/test_dynamic_discovery.py 2.7 KB runs code
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.
- 12d ago First seen · 110 lines · 52 tokens per session scan A dbad5dad4a23
common-reasoning-lenses is a skill published in the GitHub repository lihaozheCharlie/TwhWiki (24 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 1,629 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…