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 fatihguner/foreman --skill systems-thinkinggit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/systems-thinking)<a href="https://agentmods.dev/skills/fatihguner/foreman/systems-thinking"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/systems-thinking/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/fatihguner/foreman/systems-thinking"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/systems-thinking.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 | $0.00078 | $0.03535 |
| Opus 5 | $0.00039 | $0.01767 |
| Sonnet 5 | $0.00016 | $0.00707 |
| Haiku 4.5 | $0.00008 | $0.00353 |
Grade A, and why
systems-thinking 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 5d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Systems Thinking
A startup lowers its prices to win market share. Sales volume surges. The support team, sized for the previous volume, becomes overwhelmed. Response times triple. Customer satisfaction collapses. Negative reviews proliferate. The sales team, now fighting a reputation problem, demands more marketing spend to overcome the brand damage. Margins tighten. The price cut that was supposed to accelerate growth has, through a chain of consequences no single decision-maker foresaw, created a crisis that threatens the company's survival. This is not bad luck. It is a system behaving exactly as its structure dictates.
Peter Senge's The Fifth Discipline (1990) brought systems thinking into the management mainstream, though its roots extend to Jay Forrester's work at MIT in the 1950s and further back to cybernetics. The core insight is deceptively profound: the behaviour of any complex organisation is driven not by individual events or decisions but by the structure of relationships between its components. Change the events and the behaviour persists. Change the structure and the behaviour transforms.
The Framework
The Hierarchy of Understanding
Systems thinkers operate at three levels, each more powerful than the last:
Level 1: Events -- "What just happened?" Most management operates here. Revenue dropped. A key hire quit. A competitor launched a new feature. Event-level thinking produces reactive responses: cut costs, make a counter-offer, rush a feature release.
Level 2: Patterns -- "What trends are emerging?" More sophisticated. Revenue has declined for three consecutive quarters. Turnover in engineering has risen from 8% to 22% over 18 months. The competitor has released three features in our core space in the past year. Pattern-level thinking produces adaptive responses: restructure the sales team, review compensation benchmarks, reassess competitive strategy.
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.
- 5d ago First seen · 259 lines · 78 tokens per session scan A 6f08a9bb0ef5
systems-thinking is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 3,535 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 2026-09-06.
Other skills, from other repositories
Decision Helper
Make better decisions using structured frameworks and mental models.
decision-maker
Use this skill when you face a complex or high-stakes decision and need a structured framework to evaluate options objectively. Ideal for career choices, product prioritization, vendor selection, or any multi-criteria trade-off. Not for trivial daily decisions or situations that require licensed professional advice.
Decision Helper
Make better decisions using structured frameworks and mental models.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.