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 marcos-sponton/frameworks-as-skills --skill thinking-in-systemsgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-skillsWrote 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/marcos-sponton/frameworks-as-skills/thinking-in-systems)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/thinking-in-systems"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/thinking-in-systems/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/marcos-sponton/frameworks-as-skills/thinking-in-systems"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/thinking-in-systems.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00334 | $0.03751 |
| Opus 5 | $0.00167 | $0.01876 |
| Sonnet 5 | $0.00067 | $0.00750 |
| Haiku 4.5 | $0.00033 | $0.00375 |
Grade A, and why
thinking-in-systems 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking in Systems (Donella Meadows)
Donella "Dana" Meadows's systems thinking method — a way of seeing that helps you diagnose why systems produce the behaviors they produce and where interventions will actually work. Distilled from Thinking in Systems: A Primer (Chelsea Green, 2008 — posthumous, drafted around 1993, edited by Diana Wright), the canonical essay Leverage Points: Places to Intervene in a System (Whole Earth 1997, Sustainability Institute 1999), and the humility companion Dancing with Systems (1998/99). Meadows was a biophysicist, Dartmouth environmental studies professor, MacArthur Fellow (1994), and lead author of The Limits to Growth (1972). She died in February 2001; her work is carried today by the Academy for Systems Change (formerly the Sustainability Institute she founded in 1996), the Donella Meadows Project archive, and practitioners in her lineage.
This skill exists because "Meadows" is one of the most name-dropped and shallowly-applied names in the systems space. Most references invoke the 12 Leverage Points as a list without the ranking's diagnostic point, or invoke "systems thinking" without the archetypes or the Dancing-with-Systems humility. The skill helps the assistant identify which leverage point and which archetype apply to the situation on the table — and hold the ecological, non-corporate register Meadows's method actually inhabits.
When this skill activates
Use this skill when the user is:
- Diagnosing why a system (organization, market, product, program, policy, ecosystem) keeps producing the same outcome despite interventions.
- Considering an intervention and wanting to know whether it's high-leverage or low-leverage.
- Doing a post-mortem on a program / launch / policy that didn't behave as expected.
- Running root-cause analysis that keeps landing on symptoms rather than structure.
- Debating between many candidate interventions and needing to rank them.
- Reaching for an obvious fix (a target, an incentive, a threshold) for a problem that keeps recurring — a signal the fix may be at a low leverage point.
- Trying to understand a delayed, oscillating, or overshoot-and-collapse pattern.
- Trying to name what pattern this actually is (limits to growth, tragedy of the commons, shifting the burden, drift to low performance, success to the successful, escalation, fixes that fail).
- Working on ecological, sustainability, resource, or planetary-limits questions — Meadows's home register.
- Reaching for "systems thinking" language and wanting the actual method behind the phrase.
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.
- evals/evals.json 11 KB
- examples/.gitkeep 0 B
- README.md 10.0 KB
- references/applications.md 16 KB
- references/author-live-sources.md 14 KB
- references/examples.md 15 KB
- references/heuristics.md 17 KB
- references/method.md 27 KB
- references/post-book.md 17 KB
- references/prompts.md 9.1 KB
- references/sources.md 9.9 KB
- references/voice-and-tone.md 18 KB
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.
- 11d ago First seen · 104 lines · 334 tokens per session scan A c80ef48b8431
thinking-in-systems is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 334 tokens to every session and 3,751 once invoked, about $0.0017 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 skills, from other repositories
kaggle-learner
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
emotional-intelligence
Assesses and develops leadership emotional intelligence using Goleman's five-domain EQ framework: Self-Awareness, Self-Regulation, Motivation, Empathy, and Social Skill. Diagnoses interpersonal conflicts, evaluates team EQ profiles, and builds development plans for emotional competencies. Use when resolving co-founder…
flow-state
Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…
hackman-enabling-conditions
Diagnoses and designs team effectiveness using Hackman's six enabling conditions: a real team, compelling direction, right people, sound structure, supportive context, and expert coaching. Shifts focus from blaming team members to establishing the structural and environmental conditions that make high performance…
johari-window
Improves self-awareness, trust, and team communication using the Johari Window model with its four panes: Open (known to self and others), Blind Spot (known to others, not self), Hidden (known to self, not others), and Unknown. Use when building trust within teams, identifying leadership blind spots, improving…
maslow-hierarchy
Analyzes human motivation through Maslow's five-tier hierarchy of needs: physiological, safety, belonging, esteem, and self-actualization. Maps customer need levels for product positioning and employee motivation for retention strategy. Use when diagnosing employee disengagement despite good pay, repositioning product…