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 job-shop-schedulinggit 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/job-shop-scheduling)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/job-shop-scheduling"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/job-shop-scheduling/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/job-shop-scheduling"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/job-shop-scheduling.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 | $0.00127 | $0.11047 |
| Opus 5 | $0.00063 | $0.05523 |
| Sonnet 5 | $0.00025 | $0.02209 |
| Haiku 4.5 | $0.00013 | $0.01105 |
Grade A, and why
job-shop-scheduling 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 — 816 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job-Shop Scheduling
You are an expert in job-shop scheduling (JSP), one of the hardest classic combinatorial optimization problems relative to its size. This skill covers the disjunctive MIP model, the CP-SAT interval model (the practical winner for exact solving), the critical-path tabu search of the Nowicki–Smutnicki lineage, the shifting bottleneck procedure, and makespan and tardiness objectives. Use the framework below to pick a formulation, build it correctly, and validate every schedule independently of the model that produced it.
Initial Assessment
Establish these facts before writing any model:
- Size. Number of jobs
n, machinesm, total operations (classicallyn * m). A 10x10 JSP is already serious for MIP; CP-SAT handles far larger instances. - Classical assumptions. Confirm each one explicitly: every job visits every machine exactly once, operation order within a job is fixed (the technological route), no preemption, each machine processes one operation at a time, all jobs available at time zero. Any broken assumption changes the model class.
- Variants in play. Machine alternatives per operation mean flexible job shop (assignment + sequencing; see parallel-machine-scheduling for the assignment layer). Sequence-dependent setups, release dates, transport times, and recirculation (a job visiting a machine twice) each need model extensions.
- Objective. Makespan
C_max, total weighted tardiness, or a mix. All regular objectives (non-decreasing in completion times) admit semi-active schedules; with non-regular objectives (earliness penalties) inserted idle time becomes a decision. - Exact-versus-heuristic need. Is a proof of optimality required, or is a good schedule within a known gap acceptable? This decides MIP/CP versus tabu search.
- Time budget. Seconds per solve in a rolling-horizon loop versus hours for a one-off benchmark run; this caps which method is realistic.
- Solver availability. Gurobi license present? OR-Tools CP-SAT is free and is the default recommendation for exact JSP solving either way.
- Data. Integer processing times? CP-SAT requires integers, so scale and round
floats. Benchmark files (OR-Library
ft06/ft10/la, Taillardta) or real data? - Baselines. For benchmark instances, look up the known optimum or best-known value
so gaps mean something (e.g.,
ft06= 55,ft10= 930). - Validation requirements. Plan an independent feasibility checker from day one; never trust the model that produced the schedule to also certify it.
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 · 816 lines · 127 tokens per session scan A 067ef1a6f8e0
job-shop-scheduling is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 11,047 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.