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 theory-of-constraintsgit 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/theory-of-constraints)<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.
<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>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 | $0.00409 | $0.04596 |
| Opus 5 | $0.00204 | $0.02298 |
| Sonnet 5 | $0.00082 | $0.00919 |
| Haiku 4.5 | $0.00041 | $0.00460 |
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.
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.
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 12 KB
- examples/.gitkeep 0 B
- README.md 9.1 KB
- references/applications.md 12 KB
- references/author-live-sources.md 8.1 KB
- references/examples.md 12 KB
- references/heuristics.md 10 KB
- references/method.md 17 KB
- references/post-book.md 14 KB
- references/prompts.md 9.8 KB
- references/sources.md 9.2 KB
- references/voice-and-tone.md 11 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.
- 12d ago First seen · 159 lines · 409 tokens per session scan A 076dfe0bd037
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.
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.
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.
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.
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.
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…
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.