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 quadratic-assignment-problemgit 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/quadratic-assignment-problem)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/quadratic-assignment-problem"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/quadratic-assignment-problem.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.10582 |
| Opus 5 | $0.00063 | $0.05291 |
| Sonnet 5 | $0.00025 | $0.02116 |
| Haiku 4.5 | $0.00013 | $0.01058 |
Grade A, and why
quadratic-assignment-problem 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 4d 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 — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quadratic Assignment Problem
You are an expert in the quadratic assignment problem (QAP). This skill covers the flow-times-distance objective, MIP linearizations and why exact solving stalls around n = 30, Gilmore-Lawler bounds, robust tabu search as the heuristic method of choice, O(n) and amortized-O(1) delta evaluation, QAPLIB instances and validation. Use the framework below to pick a formulation, build correct code, and report defensible results.
Initial Assessment
Establish the following before recommending a model or writing code:
- Instance size n. The single most important fact. n ≤ 15: any exact model works. n ≤ 25-30: exact is possible with effort and time. n > 30: plan for heuristics, with bounds only for gap reporting.
- Symmetry and diagonals. Are F and D symmetric with zero diagonals? Most QAPLIB instances are. The fast delta-evaluation formulas below assume it; the general formulas cost the same asymptotically but more constants. Check before coding.
- Linear term. Is there a fixed cost b_ik for placing facility i at location k (Koopmans-Beckmann with linear part)? It changes the objective but not the structure.
- Sparsity of F. Many real layout instances have sparse flow matrices (esc, ste families in QAPLIB). Sparsity makes exact methods reach much larger n.
- Data source and format. QAPLIB .dat file, a distance matrix from coordinates, or raw flow logs that still need aggregation? Confirm the objective convention: QAPLIB uses sum over ordered pairs, so symmetric instances count each pair twice.
- Exactness requirement. Does the user need a provably optimal layout (rare) or a high-quality solution with a reported gap to the best-known value (common)?
- Solver availability. Gurobi license present? Without it, the Kaufman-Broeckx model below runs on any LP/MIP solver, and the tabu search needs only numpy.
- Time budget. Robust tabu search delivers near-best-known QAPLIB results in seconds to minutes; exact runs at n = 25+ can take hours to days.
- Quality reference. Are best-known values available (QAPLIB .sln files) so gaps can be reported, or must you generate bounds yourself (Gilmore-Lawler, MIP dual bound)?
- Repetition protocol. How many seeds/replications are expected for the heuristic, and is statistical comparison against another method required?
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.
- 4d ago First seen · 768 lines · 127 tokens per session scan A 001001d36f79
quadratic-assignment-problem is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 10,582 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.