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 hajibabaie/combinatorial-optimization-skills --skill milp-modeling-gurobigit clone --depth 1 https://github.com/hajibabaie/combinatorial-optimization-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/hajibabaie/combinatorial-optimization-skills/milp-modeling-gurobi)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/milp-modeling-gurobi"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/milp-modeling-gurobi/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/hajibabaie/combinatorial-optimization-skills/milp-modeling-gurobi"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/milp-modeling-gurobi.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 | $0.00141 | $0.10077 |
| Opus 5 | $0.00071 | $0.05038 |
| Sonnet 5 | $0.00028 | $0.02015 |
| Haiku 4.5 | $0.00014 | $0.01008 |
Grade A, and why
milp-modeling-gurobi 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 11d 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 — 815 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MILP Modeling with Gurobi
You are an expert in mathematical optimization and the gurobipy API. This skill covers end-to-end construction of mixed-integer linear programs: variable creation, constraint-builder functions, objectives, parameter control, solving, status handling, and solution extraction. It is the anchor exact-method skill: decomposition, cutting-plane, and matheuristic skills all assume the build-solve-extract discipline defined here. Use the framework below to turn a formulated problem into correct, maintainable, and debuggable solver code.
Initial Assessment
Establish these facts before writing any model code:
- Problem class and formulation status. Is the mathematical model already written down
(sets, parameters, variables, constraints, objective)? If not, formulate first — see
problem-formulation. Never start typing
addVaragainst a vague word problem. - Instance size. Count variables and constraints as functions of the data
(e.g., GAP has
m*nbinaries,n + mrows). Estimate nonzeros. Below ~1e6 nonzeros, build style barely matters; above it, prefer the matrix API and sparse construction. - Integrality. Which decisions are truly discrete? Every avoidable integer variable costs branching effort. Quantities that are large (hundreds of units) can often stay continuous and be rounded.
- Hard vs soft constraints. Hard constraints become rows; soft constraints become penalized slack variables in the objective. Confirm the classification with the user before coding — it changes the model skeleton.
- License and solver availability. Gurobi requires a license (free academic licenses
exist; the
pipinstall ships a size-limited trial). If there is no license, switch to open-source-solvers before investing in gurobipy-specific code. - Time budget and quality target. Proven optimality, 1% gap, or "best in 60 seconds"?
This sets
MIPGapandTimeLimitup front and decides whether a heuristic is the better tool entirely. - Data format and units. Where do coefficients come from (CSV, database, generated)? Check unit consistency: mixing cents with millions of dollars creates the numerical pathologies described under Practical Challenges.
- Re-solve pattern. One-shot solve, or repeated solves with changing data
(rolling horizon, decomposition loop)? Repeated solves favor model modification over
rebuild and explicit
Seed/Threadscontrol for reproducibility. - Deliverable. A solution table, a reusable module, or an experiment harness? This determines how much of the Output Format section applies.
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.
- 11d ago First seen · 815 lines · 141 tokens per session scan A a4aefb7aa19d
milp-modeling-gurobi is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 141 tokens to every session and 10,077 once invoked, about $0.0007 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
python-backend-expert
This skill should be used when the user is writing, reviewing, debugging, or architecting Python backend code using Litestar or FastAPI with SQLAlchemy or Advanced Alchemy. Provides expert critique covering SOLID principles, hexagonal architecture, repository/service patterns, dependency injection, async correctness…
backend-development
Use when building or structuring a Python backend on FastAPI + SQLAlchemy 2.0 (async) + Alembic + Pydantic v2. Provides the opinionated project layout, the standard kit (auth, async jobs, caching, storage, observability), and best practices.
odoo-python
Use when writing or reviewing any Python in an Odoo module — models, computes, overrides, controllers, wizards. Carries PSAE review-derived principles for ORM correctness, performance, style, and security, plus references for exact patterns. Invoke before writing logic in models/, controllers/, or wizard/.
odoo-python
Use when writing or reviewing any Python in an Odoo module — models, computes, overrides, controllers, wizards. Carries PSAE review-derived principles for ORM correctness, performance, style, and security, plus references for exact patterns. Invoke before writing logic in models/, controllers/, or wizard/.
astropy
Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.
cobrapy
Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.