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 tondevrel/scientific-agent-skills --skill ortoolsgit clone --depth 1 https://github.com/tondevrel/scientific-agent-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/tondevrel/scientific-agent-skills/ortools)<a href="https://agentmods.dev/skills/tondevrel/scientific-agent-skills/ortools"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/ortools/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/tondevrel/scientific-agent-skills/ortools"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/ortools.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 | $0.00094 | $0.02820 |
| Opus 5 | $0.00047 | $0.01410 |
| Sonnet 5 | $0.00019 | $0.00564 |
| Haiku 4.5 | $0.00009 | $0.00282 |
Grade A, and why
ortools 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 10d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google OR-Tools - Combinatorial Optimization
OR-Tools provides specialized solvers for hard combinatorial problems. Its crown jewel is the CP-SAT solver, which uses Constraint Programming and Satisfiability techniques to find optimal solutions for scheduling and resource allocation problems that are impossible for standard linear solvers.
When to Use
- Vehicle Routing (VRP): Finding the best paths for a fleet of vehicles to deliver goods.
- Scheduling: Creating shift rosters, project timelines, or job-shop schedules.
- Bin Packing: Fitting objects of different sizes into a finite number of bins.
- Knapsack Problem: Selecting items to maximize value within a weight limit.
- Linear Programming (LP): Standard resource allocation with continuous variables.
- Integer Programming (MIP): Optimization where variables must be whole numbers (e.g., "number of machines to buy").
- Network Flows: Calculating max flow or min cost in a graph.
Reference Documentation
Official docs: https://developers.google.com/optimization
GitHub: https://github.com/google/or-tools
Search patterns: cp_model.CpModel, pywraplp.Solver, routing_enums_pb2, AddConstraint
Core Principles
Modeling vs. Solving
OR-Tools separates the Definition of the problem (Variables, Constraints, Objective) from the Solver engine. You build a model, then pass it to a solver instance.
CP-SAT (Constraint Programming)
The most modern and recommended solver for discrete problems. Critical Note: CP-SAT works with integers only. If you have floating-point numbers (like 0.5), you must scale them (e.g., multiply by 100 and work with integers).
Status Codes
After solving, always check the status. It can be OPTIMAL, FEASIBLE (a solution found, but maybe not the best), INFEASIBLE (impossible to solve), or LIMIT_REACHED.
Quick Reference
Installation
pip install ortools
Standard Imports
from ortools.sat.python import cp_model
from ortools.linear_solver import pywraplp
from ortools.constraint_solver import routing_enums_pb2
from ortools.constraint_solver import pywrapcp
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.
- 10d ago First seen · 317 lines · 94 tokens per session scan A b66cdd81d89c
ortools is a skill published in the GitHub repository tondevrel/scientific-agent-skills (21 stars, last pushed 7mo ago), licensed MIT. It adds 94 tokens to every session and 2,820 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…