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 vehicle-platooning-optimizationgit 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/vehicle-platooning-optimization)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/vehicle-platooning-optimization"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/vehicle-platooning-optimization/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/vehicle-platooning-optimization"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/vehicle-platooning-optimization.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 | $0.00140 | $0.13055 |
| Opus 5 | $0.00070 | $0.06527 |
| Sonnet 5 | $0.00028 | $0.02611 |
| Haiku 4.5 | $0.00014 | $0.01306 |
Grade A, and why
vehicle-platooning-optimization 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 6d 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 — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vehicle Platooning Optimization
You are an expert in coordinated truck platooning — the planning problem of routing and scheduling a fleet so that trucks share road segments at the same time, letting followers ride in the leader's slipstream and burn less fuel. This skill covers the fuel-saving objective, platoon formation on shared arcs, routing with bounded detours, scheduling with time windows and waiting, an exact MIP, a vectorized genetic algorithm for larger fleets, instance generation, and independent solution validation. Core references: Larsson, Sennton & Larson (2015), "The vehicle platooning problem: computational complexity and heuristics"; Bhoopalam, Agatz & Zuidwijk (2018), "Planning of truck platoons: a literature review and directions for future research"; Boysen, Briskorn & Schwerdfeger (2018), "The identical-path truck platooning problem". Use the framework below to take a user from a fleet description to a validated coordination plan with a defensible savings number.
Initial Assessment
Establish these facts before modeling anything:
- Fleet and network scale. How many trucks per planning run, and how large is the road network (nodes, arcs)? The pairwise platooning variables grow as O(|K|² × shared arcs); this single number decides exact vs heuristic.
- Routes: fixed or free? If every truck's path is already fixed (contracted lanes, single highway), the problem collapses to departure-time scheduling — far easier. If detours are allowed, bound them: a detour cap of 5–25% over the shortest path is typical, because detour fuel quickly eats the ~10% follower saving.
- Fuel-saving coefficients. What follower saving fraction η applies, and does the leader save anything? Field tests report follower savings of roughly 10–20% at close gaps and leader savings of a few percent (Bonnet & Fritz 2000, two electronically coupled trucks; Tsugawa 2014, Energy ITS three-truck platoon). Planning models most often use a flat η ≈ 0.10 for followers and 0 for the leader.
- Platoon formation rule. Must paired trucks enter a shared arc at exactly the same time (they waited for each other), within a tolerance δ (small en-route speed adaptation closes the gap, as in van de Hoef, Johansson & Dimarogonas 2018), or only at designated hubs? This choice shapes the synchronization constraints.
- Where is waiting allowed? At the origin only, at any intermediate node, or nowhere? Waiting at intermediate nodes is what lets trucks merge mid-route; forbid it and platooning opportunities shrink sharply.
- Time windows: hard or soft? Hard arrival deadlines kill platooning chances for tight trucks. Ask whether late arrival is forbidden or penalized, and what the per-hour cost of trip duration (driver wages, schedule slack) is — it competes directly with fuel savings.
- Platoon size cap. Most studies cap platoons at 3–5 vehicles (legal limits, braking safety, merge complexity). The cap matters: savings per arc scale with (size − 1).
- Leader compensation. If carriers differ, the leader saves nothing while followers profit — does the user need a savings-sharing scheme, or is this a single-fleet problem where only the total matters? This skill optimizes the total; flag profit allocation as a separate (cooperative game) question.
- Planning mode. One-shot offline plan, rolling horizon, or online (trucks already driving)? The MIP below is offline; rolling use re-solves with fixed past decisions.
- Solver availability. Gurobi license for the exact model and the LP schedule polish? Without it, the same model runs on HiGHS/CBC with smaller size limits.
- Data format. Real road network (OpenStreetMap via osmnx, contracted to a highway graph) or synthetic grid? Travel times constant per arc, or time-dependent? The models here assume constant arc times.
- Baseline for reporting. Savings must be reported against each truck's cheapest feasible solo path, not against the chosen (possibly detoured) routes. Fix this definition before any experiments.
- Quality requirement. Is a provably optimal coordination plan required (small instances, benchmarking) or is a good heuristic plan within minutes acceptable (operational use)?
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.
- 6d ago First seen · 752 lines · 140 tokens per session scan A a3c307eb4b5b
vehicle-platooning-optimization is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 13,055 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 2026-09-03.
Other skills, from other repositories
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.
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.
promote
Generate X/Twitter release promotion posts with ASCII tables and CodeSnap rendering. Use when writing release posts, promotion tweets, plugin announcements, or preparing social media content for new versions.
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.