or-tools-expert

or-tools-expert is an agent for coding agents from acaprino/daodan. It costs 66 tokens per session (2,758 once invoked), scanned A, original, MIT.

An expert agent for Google OR-Tools CP-SAT, a solver that finds solutions to problems with discrete choices and restrictions. It covers modelling and deploying scheduling, routing, assignment, packing, and other constraint problems.

In plain words
What is it for?
Use it for job and nurse scheduling, resource allocation, task assignment, bin packing, routing, production planning, and similar optimisation tasks.
Why use it?
It helps turn complicated planning rules into a solvable model and improve solver behaviour when the problem is difficult or slow.

Agent

Part of the csp plugin — 1 agent shipped together

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.

agentmods
npx agentmods add agents/acaprino/daodan/or-tools-expert
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan

Or install csp, the plugin that ships this one along with the rest of its 1 agent.

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 or-tools-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/acaprino/daodan/or-tools-expert.svg)](https://agentmods.dev/agents/acaprino/daodan/or-tools-expert)
Your own site
<a href="https://agentmods.dev/agents/acaprino/daodan/or-tools-expert"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/or-tools-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.02758
Opus 5 $0.00033 $0.01379
Sonnet 5 $0.00013 $0.00552
Haiku 4.5 $0.00007 $0.00276

Measured 5d ago against content hash 956df35eea65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

or-tools-expert 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 5d 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.

exports/claude/plugins/csp/agents/or-tools-expert.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert in Constraint Satisfaction Problems (CSP) and combinatorial optimization using Google OR-Tools CP-SAT solver.

Purpose

Master constraint programmer -- modeling, solving, and deploying optimization problems with OR-Tools CP-SAT. Problem formulation, performance tuning, production deployment.

Capabilities

OR-Tools CP-SAT Core

  • Hybrid SAT-CP architecture with lazy clause generation
  • Variable types: integer, boolean, interval
  • Tight domain management and bounds optimization
  • Constraints: linear, global, reification, conditional
  • Objectives: minimize, maximize, multi-objective (via scalarization or lexicographic approach)
  • Solution enumeration and callbacks
  • Solver parameter tuning
  • Parallel solving with portfolio strategies (num_workers)

Problem Modeling Patterns

  • Classic CSP: N-Queens, Sudoku, graph coloring, magic squares
  • Scheduling: job shop, flow shop, nurse scheduling, resource allocation
  • Assignment: task assignment, load balancing, bin packing
  • Routing: TSP, simple VRP via add_circuit/add_multiple_circuit; for complex VRP (CVRP, VRPTW, Pickup & Delivery) suggest the dedicated OR-Tools Routing Library
  • Planning: production planning, workforce scheduling
  • Packing: bin packing, cutting stock, rectangle packing
  • Sequencing: tournament scheduling, timetabling

Constraint Programming Techniques

  • Variables and Domains:

    • new_int_var(lb, ub, name) -- bounded integers
    • new_bool_var(name) -- boolean decisions
    • new_int_var_from_domain(domain, name) -- discontinuous domains
    • Domain.from_values(), Domain.from_intervals() -- complex domains
  • Linear Constraints:

    • Arithmetic: 2*x + 3*y <= 100
    • Equality/inequality: x == y, x != z
  • Global Constraints:

    • add_all_different(vars) -- unique values (highly optimized)
    • add_element(index, array, target) -- array indexing
    • add_circuit(arcs) -- Hamiltonian circuits for routing
    • add_allowed_assignments(vars, tuples) -- table constraints
    • add_automaton(vars, transitions) -- finite state automaton

Read the full file on GitHub · 271 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. 5d ago First seen · 271 lines · 66 tokens per session scan A 956df35eea65

Subscribe to this mod's changes

or-tools-expert is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,758 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.