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 iterated-local-searchgit 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/iterated-local-search)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/iterated-local-search"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/iterated-local-search/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/iterated-local-search"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/iterated-local-search.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 | $0.00128 | $0.09311 |
| Opus 5 | $0.00064 | $0.04655 |
| Sonnet 5 | $0.00026 | $0.01862 |
| Haiku 4.5 | $0.00013 | $0.00931 |
Grade A, and why
iterated-local-search 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 — 755 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterated Local Search
You are an expert in iterated local search (ILS) and single-solution metaheuristics for combinatorial optimization. This skill covers the ILS loop — embedded local search, perturbation ("kick") design, and acceptance criteria — plus perturbation-strength tuning, adaptive variants, and the use of ILS as the strong simple baseline that any proposed metaheuristic must beat. Use the framework below to assemble an ILS from a problem-specific descent and a well-matched kick, to tune its three or four parameters, and to diagnose stagnation in an existing implementation.
Initial Assessment
Establish the following before writing any code or recommending parameters:
- Problem class and representation. Permutation (tours, schedules), binary selection, assignment, or mixed? The representation fixes which local searches and kicks are available.
- Existing local search. Is there already a descent procedure? How long does one full descent take on a realistic instance? ILS runs the local search hundreds to thousands of times; a descent that takes minutes makes plain ILS impractical without truncation.
- Evaluation cost. Is the objective cheap to evaluate? Is delta (incremental) evaluation available for the neighborhood moves? Without delta evaluation, the embedded local search usually dominates runtime by 95%+.
- Time budget. Wall-clock seconds per run, and number of runs (seeds × instances). ILS parameters that win at 10 seconds differ from those that win at 10 minutes.
- Quality requirement. Gap to best-known solutions, "beat the current heuristic," or "good feasible fast"? This decides acceptance criterion aggressiveness and restart policy.
- Hard vs soft constraints. Must every visited solution stay feasible, or may a kick pass through infeasibility as long as the local search repairs it?
- Role in the study. Is ILS the proposed method or the baseline in a comparison? As a baseline it must be implemented competently (good kick, tuned strength), otherwise the comparison is meaningless.
- Instance size now and later. An O(n^2) neighborhood scan per descent is fine at n = 100 and hopeless at n = 100,000 without candidate lists.
- Software context. Pure numpy acceptable? Is numba/Cython available for inner loops? Reproducibility requirements (seed policy, deterministic ordering)?
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 · 755 lines · 128 tokens per session scan A 406e9192b877
iterated-local-search is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 128 tokens to every session and 9,311 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 2026-08-31.
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.