systems-thinking

systems-thinking is a skill for Claude Code, Codex from fzfclee/consulting-skills. It costs 51 tokens per session (1,281 once invoked), scanned A, original, Apache-2.0.

A method for understanding how parts of a system affect one another over time, including feedback loops, delays, incentives, and constraints. A system can be a team, process, market, or technical setup.

In plain words
What is it for?
Mapping causes and relationships, finding points where a small change may help, and diagnosing problems involving many interacting actors or components.
Why use it?
It reveals recurring patterns and unintended consequences that a simple one-cause explanation may miss.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Mapping causes and relationships, finding points where a small change may help, and diagnosing problems involving many interacting actors or components.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fzfclee/consulting-skills/systems-thinking
Install

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.

Any agent
npx skills add fzfclee/consulting-skills --skill systems-thinking
Clone the repo
git clone --depth 1 https://github.com/fzfclee/consulting-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for systems-thinking

README.md
[![agentmods](https://agentmods.dev/badge/skills/fzfclee/consulting-skills/systems-thinking/github.svg)](https://agentmods.dev/skills/fzfclee/consulting-skills/systems-thinking)
Your own site
<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/systems-thinking"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/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.

agentmods 80×15 button for systems-thinking

Your own site · 80×15
<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/systems-thinking"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/systems-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,281 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01281
Opus 5 $0.00026 $0.00641
Sonnet 5 $0.00010 $0.00256
Haiku 4.5 $0.00005 $0.00128

Measured 8d ago against content hash 0d08dc858db2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 8d 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.

skills/systems-thinking/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systems Thinking

Use this skill to understand how parts of a system interact and why behavior persists over time.

Method Notes

  • Systems thinking focuses on relationships, feedback loops, delays, incentives, and patterns.
  • It is useful when direct cause-and-effect explanations are too shallow.
  • The goal is to identify leverage points, not to draw a complicated map for its own sake.
  • Keep the system boundary explicit so the analysis stays usable.

Required Inputs

Collect or infer these inputs before execution:

  • system or problem boundary
  • actors, components, processes, or variables
  • repeated pattern or outcome
  • incentives, constraints, and feedback signals
  • time horizon and behavior-over-time pattern
  • time delays or unintended consequences
  • evidence for relationship direction, loop logic, and expected trend

If an input is missing, mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use when the issue is a one-off decision with stable criteria. Use decision-matrix, deductive-reasoning, or risk-matrix instead.

Adjacent Methods

  • five-whys-root-cause: one linear cause chain.
  • fishbone-diagram: several operational cause categories.
  • constraint-analysis: one binding bottleneck.

Step-by-Step Execution

Step Required input How to execute Output
Select level and boundary Decision need, scope, time horizon, available evidence. Choose L0 for a qualitative dynamic map or L1 when a proposed intervention must be stress-tested. State what is inside, outside, and not modeled. Level statement and system boundary.
Describe behavior over time Outcome history, trend, recurring episodes, baseline. Describe the pattern before explaining it: growth, decline, oscillation, plateau, overshoot, or repeated return. Mark missing time-series evidence. Behavior-over-time pattern.
Identify key variables Actors, resources, decisions, behaviors, metrics, constraints. Keep only variables that can materially change the outcome within the chosen horizon. Mark owner and evidence strength. Decision-relevant variable list.
Map directional relationships Variables, observations, causal evidence. For each link, state whether the source increases or decreases the target, assign positive, negative, or unknown polarity, and mark delay and evidence. Signed relationship map.
Close feedback loops Signed relationships. Trace closed paths. Label reinforcing loops that amplify change and balancing loops that counter it. Do not call an open chain a loop. Named R/B loops and dominant conditions.
Add delays, incentives, and constraints Process timing, rules, rewards, decision rights. Show where response is delayed, which incentives create behavior, and which constraints limit adjustment. Dynamic mechanism diagnosis.
Identify leverage points Loops, constraints, control rights, intervention options. Find changes that alter information, incentives, rules, capacity, delay, or decision rights. Rate controllability and evidence. Ranked leverage points.
Stress-test intervention Proposed action, loops, delay, affected actors. Predict direction over time, lag, compensating response, side effects, and problem displacement. Define a lower-regret version. L1 intervention stress test.
Define learning loop Expected trend, leading indicators, review cadence. Set signals, thresholds, owner, review date, and the assumption that must be revised if the pattern differs. Monitoring and model-revision plan.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 8d ago First seen · 103 lines · 51 tokens per session scan A 0d08dc858db2

Subscribe to this mod's changes

systems-thinking is a skill published in the GitHub repository fzfclee/consulting-skills (4 stars, last pushed 20d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,281 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 2026-08-31.