theory-of-constraints

theory-of-constraints is a skill for Claude Code, Codex from marcos-sponton/frameworks-as-skills. It costs 409 tokens per session (4,596 once invoked), scanned A, original, MIT.

A planning method that finds the one part of a system limiting its overall progress, then improves it step by step. It is based on Eliyahu Goldratt’s Theory of Constraints.

In plain words
What is it for?
Use it to improve production processes, manage projects, measure throughput, inventory, and operating expense, and plan work using methods such as Drum-Buffer-Rope or Critical Chain.
Why use it?
It helps avoid spreading effort across many problems when one bottleneck is controlling the result. The method also helps coordinate work around that bottleneck.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to improve production processes, manage projects, measure throughput, inventory, and operating expense, and plan work using methods such as Drum-Buffer-Rope or Critical Chain.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcos-sponton/frameworks-as-skills/theory-of-constraints
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 marcos-sponton/frameworks-as-skills --skill theory-of-constraints
Clone the repo
git clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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 theory-of-constraints

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/theory-of-constraints/github.svg)](https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/theory-of-constraints)
Your own site
<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/theory-of-constraints"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/theory-of-constraints/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 theory-of-constraints

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/theory-of-constraints"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/theory-of-constraints.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 409 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,596 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 $0.00409 $0.04596
Opus 5 $0.00204 $0.02298
Sonnet 5 $0.00082 $0.00919
Haiku 4.5 $0.00041 $0.00460

Measured 12d ago against content hash 076dfe0bd037, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

theory-of-constraints 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 12d 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/theory-of-constraints/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Theory of Constraints — an agent skill

Eliyahu M. Goldratt (1947–2011) — Israeli physicist turned management theorist. Founder of the Theory of Constraints (TOC), introduced through the business novel The Goal (1984, w/ Jeff Cox), the best-selling business novel of all time (7M+ copies, translated into 35 languages). Continued through It's Not Luck (1994), Critical Chain (1997), Necessary But Not Sufficient (2000), Isn't It Obvious? (2006), The Choice (2008), the Goldratt Satellite Program, and Beyond the Goal (2005). Died June 11, 2011.

The ongoing work is carried by a small set of named stewards — his son Rami Goldratt (CEO of Goldratt Consulting Group), his daughter Efrat Goldratt-Ashlag (organizational psychologist; author of Goldratt's Rules of Flow, 2023, and co-author of The Choice), TOCICO as the standards body, and independent practitioners who have translated TOC into modern domains — most importantly Gene Kim, Kevin Behr, and George Spafford (The Phoenix Project, 2013), Clarke Ching (Rolling Rocks Downhill, The Bottleneck Rules), and Steve Tendon (The Book of TameFlow, 2020).

This skill helps the assistant think in Goldratt's method — not just parrot "find the bottleneck." TOC is three interlocking layers: (a) the Goal + three measurements (Throughput / Inventory / Operating Expense) that replace cost-accounting mental models; (b) the Five Focusing Steps as the operating loop, with Drum-Buffer-Rope for production and Critical Chain for projects; (c) the five Thinking Processes (Current Reality Tree, Evaporating Cloud, Future Reality Tree, Prerequisite Tree, Transition Tree) for constraints that are policies, beliefs, or conflicts rather than machines. Reducing TOC to "identify the bottleneck" loses 90% of the method.

When this skill activates

Use this skill when the user is:

  • Diagnosing why a system (plant, team, pipeline, org) is slow, late, or stuck — especially when local metrics look fine but the whole under-delivers.
  • Redesigning production scheduling, ops flow, or capacity planning — DBR territory.
  • Planning a project with a hard deadline where estimates keep slipping — Critical Chain territory (multitasking, student syndrome, Parkinson's-in-projects).
  • Being told "we need every resource at 100% utilization" — push back with the exploit/subordinate distinction.
  • Watching a Six Sigma / Lean initiative flatten because it treats every problem as equal — TOC prioritizes ruthlessly.
  • Converting cost-accounting thinking into throughput thinking — pricing "unprofitable" orders that fill constraint time, killing product-cost-based decisions.
  • Stuck in an org conflict that keeps recurring — probably an Evaporating Cloud waiting to be drawn.
  • Reading The Phoenix Project or hearing about "The Three Ways" and wondering how they connect to Goldratt.
  • Doing a POOGI (Process of Ongoing Improvement) cycle and needing to move from one constraint to the next without inertia dragging the old rules along.
  • Any conversation that names Goldratt, TOC, The Goal, Alex Rogo, Jonah, DBR, CCPM, TP, throughput accounting.

Read the full file on GitHub · 159 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. 12d ago First seen · 159 lines · 409 tokens per session scan A 076dfe0bd037

Subscribe to this mod's changes

theory-of-constraints is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 409 tokens to every session and 4,596 once invoked, about $0.0020 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.

Related

Other skills, from other repositories

acquire-skills

Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.

martineserios/thebrana · 45 tokens

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

rexleimo/aios · 67 tokens

endpoint-discovery

Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.

zebbern/termstack · 50 tokens

param-miner

Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.

zebbern/termstack · 42 tokens

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens