systems-thinking

systems-thinking is a skill for Claude Code from ysskrishna/ai-agent-skills. It costs 125 tokens per session (805 once invoked), scanned A, original, MIT.

A method for examining how parts of a system affect one another over time, including feedback loops, delays, resources, and points where a change can have a larger effect.

In plain words
What is it for?
Use it to map a system, understand its behavior, and produce recommendations that account for dependencies and delayed effects.
Why use it?
It helps avoid fixing one part of a problem while creating new problems elsewhere.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-agent-skills plugin — 10 skills shipped together

Good fit Use it to map a system, understand its behavior, and produce recommendations that account for dependencies and delayed effects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ysskrishna/ai-agent-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 ysskrishna/ai-agent-skills --skill systems-thinking
Clone the repo
git clone --depth 1 https://github.com/ysskrishna/ai-agent-skills

Made for: Claude Code.

Or install ai-agent-skills, the plugin that ships this one along with the rest of its 10 skills.

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/ysskrishna/ai-agent-skills/systems-thinking/github.svg)](https://agentmods.dev/skills/ysskrishna/ai-agent-skills/systems-thinking)
Your own site
<a href="https://agentmods.dev/skills/ysskrishna/ai-agent-skills/systems-thinking"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-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/ysskrishna/ai-agent-skills/systems-thinking"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/systems-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 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 $0.00125 $0.00805
Opus 5 $0.00063 $0.00402
Sonnet 5 $0.00025 $0.00161
Haiku 4.5 $0.00013 $0.00081

Measured 9d ago against content hash 9050edccfe77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systems Thinking

See the whole before optimizing parts. End with leverage-aware recommendations.

How to run it with this skill: one clearly headed section per phase in this order: Boundary → Structure → Dynamics → Delays → Leverage → Synthesis. Do not skip Structure before Leverage.


Setup (run before starting)

In one short block:

  1. System in focus — what is inside the boundary?
  2. Default pass — Boundary → Structure → Dynamics → Delays → Leverage → Synthesis (state this line)

If the boundary is unclear, ask at most 3 scoping questions in one message, then proceed. Note any remaining gaps or working guesses in plain language (no bracket tags in Setup).

If the user already named a proposed intervention, you may spend less text on Boundary but still must not skip Structure before Leverage.


The Phases

Boundary

What is in vs out of the system for this analysis? State the purpose of the system from a stakeholder view (one sentence).

Structure

Elements (stocks: things that accumulate; actors; resources) and flows (rates in/out). Use short bullet pairs: From → To with what moves.

Dynamics

Identify at least one reinforcing (R) and one balancing (B) loop if plausible. Format:

Loop [R|B]: … — Mechanism:

If a loop does not apply, say so in one line and justify.

Delays

Where is time lag between action and effect? How does delay change behavior (overshoot, oscillation, learned helplessness)?

Leverage

Leverage point: … — Why it matters: … — Risk of backfire:

Prefer interventions that change rules, information flows, or goals over name-and-shame unless evidence supports it; favor levers that shift incentives rather than only blaming individuals.

Synthesis

  1. System story — one paragraph in plain language (no jargon wall)
  2. Non-obvious consequence — at least one
  3. Recommended moves — 2–3 actions compatible with the map (not contradicted by delays/loops)

Read the full file on GitHub · 93 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. 9d ago First seen · 93 lines · 125 tokens per session scan A 9050edccfe77

Subscribe to this mod's changes

systems-thinking is a skill published in the GitHub repository ysskrishna/ai-agent-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 805 once invoked, about $0.0006 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.