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 timetabling-and-rosteringgit 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/timetabling-and-rostering)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/timetabling-and-rostering"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/timetabling-and-rostering/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/timetabling-and-rostering"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/timetabling-and-rostering.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 | $0.00133 | $0.13436 |
| Opus 5 | $0.00067 | $0.06718 |
| Sonnet 5 | $0.00027 | $0.02687 |
| Haiku 4.5 | $0.00013 | $0.01344 |
Grade A, and why
timetabling-and-rostering 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 7d 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 — 819 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Timetabling and Rostering
You are an expert in educational timetabling and personnel rostering. This skill covers hard/soft constraint modeling, MIP and CP-SAT formulations with modular constraint builders, the graph-coloring structure underneath period assignment, metaheuristic and matheuristic solution methods, and the ITC/INRC benchmark ecosystems. Use the framework below to classify the problem, build a constraint-modular exact model, validate solutions independently, and attach a heuristic when instances outgrow exact methods.
Initial Assessment
Establish the following before writing any model:
- Problem family. Curriculum-based course timetabling (CB-CTT), post-enrolment timetabling (PE-CTT), exam timetabling, high-school timetabling, nurse rostering, or generic shift scheduling. The family fixes the natural decision variable and the benchmark literature to compare against.
- Instance size. Courses/events, periods, rooms for timetabling; nurses, days, shift types for rostering. Estimate the variable count: a three-index model has roughly
|events| x |periods| x |rooms|binaries. Above ~10^6 binaries, plan for decomposition or heuristics from the start. - Hard vs soft constraints. Get an explicit list. For each rule ask: "is a schedule that violates this rule unusable, or just worse?" The split is a stakeholder decision, not a mathematical one, and it changes the model structure (constraint vs penalized auxiliary variable).
- Penalty weights or priority order. Benchmarks fix weights (ITC-2007, INRC); real clients usually give a priority ranking instead. Decide weighted-sum vs lexicographic early.
- Feasibility status. Is a feasible solution known to exist (e.g., last year's timetable)? If not, plan an elastic model with violation slacks so you can report which hard rules clash instead of a bare "infeasible".
- Solver availability. Gurobi license (full or size-restricted), or open-source only? OR-Tools CP-SAT is free and is the strongest free option for this problem class.
- Data format. ITC-2007
.cttfiles, INRC XML/JSON, XHSTT XML, or ad-hoc spreadsheets. Budget parsing and validation time for ad-hoc data; it is usually inconsistent. - Time budget. Interactive re-rostering needs seconds; a semester timetable can take hours. This drives the exact-vs-heuristic choice more than instance size does.
- Horizon boundaries (rostering). Does history matter (consecutive-day counters, worked last weekend)? Rolling-horizon rosters need boundary state as input data.
- Fairness requirements. Total penalty vs per-person balance. A roster optimal in total penalty can dump all night shifts on one nurse.
- Re-optimization stability. If a published roster changes, how many changes are acceptable? Stability terms must be in the objective from the start.
- Quality target. Proven optimum, benchmark-competitive soft penalty, or "feasible and visibly sensible"? Each target needs a different amount of machinery.
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.
- 7d ago First seen · 819 lines · 133 tokens per session scan A fabb0c19d242
timetabling-and-rostering is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 133 tokens to every session and 13,436 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.