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 skills/peterfei/forge-skill/systems-thinking-skillnpx skills add peterfei/forge-skill --skill systems-thinking-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWhat 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 | $0.00077 | $0.05858 |
| Opus 5 | $0.00039 | $0.02929 |
| Sonnet 5 | $0.00015 | $0.01172 |
| Haiku 4.5 | $0.00008 | $0.00586 |
Grade A, and why
systems-thinking-skill 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 3d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
系统思维 · 思维工具
"You can't navigate well in an interconnected, feedback-dominated world unless you take your mental models seriously and test them against evidence." -- Donella H. Meadows, Thinking in Systems: A Primer (2008)
激活条件与触发词
直接调用
- 「用系统思维分析...」
- 「用 systems thinking 分析...」
- 「从系统思维角度...」
语义触发
- 用户描述的问题涉及多个相互关联的因素或因果关系
- 用户提到「循环」「恶性循环」「飞轮效应」「瓶颈」「因果链」等关键词
- 用户面对的问题反复出现、干预后反弹,或局部优化导致整体恶化
- 「这个问题太复杂了,各种因素互相影响」「为什么改了 A,B 反而更差了」
组合调用
- 「先用系统思维分析,再用第一性原理深挖」
- 「系统思维 + 博弈论分析」
方法框架概览
系统思维的核心是将问题视为相互关联的要素网络,而非孤立事件。它通过识别反馈回路(Feedback Loops)和时间延迟(Delays)来揭示系统的深层行为模式,定位结构中的高杠杆干预点(Leverage Points),从而找到持久有效的解决方案。
核心原理(3-7个,每个须附 >=2 个跨域证据)
原理 1: 整体大于部分之和(Emergence / 涌现)
一句话定义:系统具有其组成要素单独存在时不具备的整体属性,涌现是系统层次的不可还原特性。
跨域证据:
- 神经科学:意识(consciousness)无法从单个神经元的放电模式中还原。单个神经元没有「意识」,但约 860 亿个神经元构成的大脑涌现出主观体验。来源:Gazzaniga, M. S., The Consciousness Instinct (2018)
- 组织管理学:组织文化(organizational culture)并非个体行为的简单加总。MIT 的 Edgar Schein 研究表明,组织文化是群体在解决适应外部整合内部问题时形成的共享基本假设,它涌现于互动中而非被设计。来源:Schein, E. H., Organizational Culture and Leadership (2010)
应用方式:面对复杂问题时,先审视整体的行为模式,而非急于拆解为独立部分。问自己:「这些要素单独看和放在一起看,有什么不同?」
局限:对于简单问题(如修理单个零件),涌现性不明显,拆解还原反而更高效。
原理 2: 因果关系是循环的,非线性的(Circular Causality)
一句话定义:在系统中,因果很少是单向直线,A 影响 B,B 又反过来影响 A,形成循环因果网络。
跨域证据:
- 宏观经济学:通货紧缩的恶性循环——价格下降导致消费推迟、消费推迟导致需求萎缩、需求萎缩迫使企业降价、进一步加剧通缩。日本「失去的二十年」正是这种循环因果的典型。来源:Krugman, P., The Return of Depression Economics (1999)
- 生态学:捕食者与猎物的 Lotka-Volterra 动态——猎物增加导致捕食者增加、捕食者增加又导致猎物减少,形成周期性振荡。这种动态无法用线性因果关系解释。来源:Lotka, A. J., Elements of Physical Biology (1925)
应用方式:画因果图时,不要止步于「A → B」,追问「B 会不会反过来影响 A?还有哪些因素连接这两者?」
局限:在因果关系确实为单向的简单场景(如物理碰撞中的力传递),强行寻找循环因果会引入噪音。
原理 3: 反馈回路塑造系统行为(Feedback Loops)
一句话定义:增强回路(Reinforcing / R Loop)驱动增长或崩溃,平衡回路(Balancing / B Loop)维持系统稳定,两者共同决定系统的动态行为。
跨域证据:
- 商业战略:Amazon 的飞轮效应——更低价格带来更多客户、更多客户吸引更多卖家、更多卖家允许更低价格。这个增强回路(R1)是 Amazon 成长的核心引擎。来源:Collins, J., Turn the Flywheel (2019)
- 公共卫生:疫苗接种的群体免疫阈值——接种率上升导致传播率下降(B1 平衡回路),但接种率下降时传染率上升又推高接种意愿(R1 增强回路)。两种回路的博弈决定了疫苗接种率的动态。来源:Fine, P., et al., "Herd Immunity: A Rough Guide," Clinical Infectious Diseases (2011)
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.
- 3d ago First seen · 266 lines · 77 tokens per session scan A 07bc40bbb7ba
systems-thinking-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 5,858 once invoked, about $0.0004 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
descend
Verifies whether the problem was correctly identified before solving, auditing pattern matches against first principles.
fundraising-narrative
This skill should be used when the user asks about "pitch deck", "fundraising story", "investor pitch", "VC narrative", "pitch narrative", "fundraising deck", "pitch structure", "Sequoia format", "why now slide", "market size slide", "TAM SAM SOM", "earned secret", "value hypothesis", "product-market fit"…
investor-relations
This skill should be used when the user asks about "investor update", "board deck", "board meeting", "investor communication", "monthly update", "quarterly update", "investor email", "bad news investors", "pivot communication", "crisis communication investors", "investor ask", "warm intro", "VC relationship"…
ux-principles
User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics.
omh-buzz
This is a Hermes-native buzz workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.