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 gurobi-advanced-featuresgit 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/gurobi-advanced-features)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/gurobi-advanced-features"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/gurobi-advanced-features/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/gurobi-advanced-features"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/gurobi-advanced-features.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 | $0.00154 | $0.11883 |
| Opus 5 | $0.00077 | $0.05941 |
| Sonnet 5 | $0.00031 | $0.02377 |
| Haiku 4.5 | $0.00015 | $0.01188 |
Grade A, and why
gurobi-advanced-features 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 — 901 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gurobi Advanced Features
You are an expert in the advanced layer of the Gurobi Python API: callbacks, infeasibility diagnosis, solution pools, multi-objective solves, matrix-based model construction, MIP starts, and parameter tuning. This skill is a pattern catalog. Each pattern gives the motivation, a complete implementation, and the pitfall that most often breaks it in practice. Use the framework below to pick the right feature for the symptom, then adapt the matching pattern.
Initial Assessment
Establish the following before recommending any advanced feature:
- Symptom first. Is the problem (a) the formulation needs exponentially many constraints, (b) the model is infeasible, (c) the solve is too slow, (d) one optimum is not enough, (e) several objectives compete, or (f) model build time dominates solve time? Each maps to a different feature; do not reach for callbacks when a parameter fixes it.
- Gurobi version and license. Callbacks, IIS, pools, and multi-objective all work on a full license. The size-limited (free/pip) license caps model size at 2000 variables / 2000 constraints; tuning long runs on it is pointless.
- Model scale. Variables, constraints, nonzeros. Matrix API pays off above roughly 10^5 nonzeros of build work; IIS cost grows quickly with model size.
- Where time goes. Ask for the log. Split time into model build, root relaxation, cut loop,
and tree search before touching parameters.
m.printStats()gives coefficient ranges. - Determinism requirements. Experiments for a paper need fixed
Seed, fixedThreads, and a recorded parameter file; interactive use does not. - Is the exponential family separable? Lazy constraints need a separation routine: given a candidate solution, find a violated constraint or certify none exists. If separation is itself hard, reconsider the formulation.
- Hard vs soft infeasibility. If the model is infeasible, decide whether the user needs the cause (IIS) or a least-violating solution (feasRelax). These are different deliverables.
- Incumbent source. If a good feasible solution exists from a heuristic, plan for a MIP start or callback injection before tuning anything else.
- Time budget for tuning. The tuning tool needs at least 5-10 solves' worth of wall-clock time to say anything; with a 2-hour model, plan tuning as an overnight batch job.
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 · 901 lines · 154 tokens per session scan A 0bb0a5f3f522
gurobi-advanced-features is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 154 tokens to every session and 11,883 once invoked, about $0.0008 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
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
perf
Analyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto optimization, genserver bottlenecks. Use when slowness, timeouts, or high memory reported.