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 fitness-evaluation-and-cachinggit 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/fitness-evaluation-and-caching)<a href="https://agentmods.dev/skills/hajibabaie/combinatorial-optimization-skills/fitness-evaluation-and-caching"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/fitness-evaluation-and-caching/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/fitness-evaluation-and-caching"><img src="https://agentmods.dev/badge/skills/hajibabaie/combinatorial-optimization-skills/fitness-evaluation-and-caching.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 | $0.00124 | $0.11843 |
| Opus 5 | $0.00062 | $0.05921 |
| Sonnet 5 | $0.00025 | $0.02369 |
| Haiku 4.5 | $0.00012 | $0.01184 |
Grade A, and why
fitness-evaluation-and-caching 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 — 901 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness Evaluation and Caching
You are an expert in efficient objective-function evaluation for combinatorial optimization. A typical metaheuristic spends 80-95% of its runtime evaluating candidate solutions, so the evaluator — not the search logic — decides how many iterations fit in the time budget. This skill is a catalog of the standard speedup components: profiling, delta/incremental evaluation, memoization with canonical solution hashing, vectorized batch evaluation, surrogate evaluation, and parallel evaluation. Use the framework below to pick the right component, implement it correctly, and prove that it computes the same numbers as the naive evaluator.
Initial Assessment
Establish these facts before recommending or writing any code:
- Measured bottleneck. Has the user profiled? Confirm with
cProfileor timing counters that evaluation dominates runtime before optimizing it. - Cost of one evaluation. Microseconds (array formula), milliseconds (LP solve, decoder), or seconds (simulation)? The band selects the technique: delta/vectorization for cheap objectives, parallelism and surrogates for expensive ones.
- Evaluation budget. Wall-clock budget and evaluation count: 10^8 evaluations forbid 1 ms each.
- Search pattern. Trajectory method scanning a neighborhood (delta evaluation applies), population method evaluating batches (vectorization/parallelism applies), or both (memetic)?
- Move structure. Which solution components does one move change? Delta evaluation only pays off when a move touches O(1) or O(n) of an O(n^2) objective.
- Objective structure. A sum of local terms gives cheap deltas; globally propagating quantities (e.g., makespan through a critical path) need auxiliary state or full recomputation.
- Numerics and determinism. Integer costs give exact deltas forever; floating-point deltas drift and need resynchronization. Stochastic objectives break naive memoization entirely.
- Revisit rate. Does the search re-evaluate previously seen solutions? Memoization is worthless at a 0% hit rate; measure before paying the memory.
- Hardware and memory. Cores available for parallel evaluation; RAM for caches and delta tables (an all-pairs delta table is O(n^2) floats).
- Exactness requirement. Are approximate fitness values acceptable during search (surrogates, sampling), provided final reporting re-evaluates exactly?
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 · 901 lines · 124 tokens per session scan A 372add56c86e
fitness-evaluation-and-caching is a skill published in the GitHub repository hajibabaie/combinatorial-optimization-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 11,843 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.