SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 agentmods add skills/benchflow-ai/skillsbench/map-optimization-strategynpx skills add benchflow-ai/skillsbench --skill map-optimization-strategygit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/map-optimization-strategy)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/map-optimization-strategy"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/map-optimization-strategy.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00967 |
| Opus 5 | $0.00017 | $0.00483 |
| Sonnet 5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
map-optimization-strategy 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- map-optimization-strategy — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Map-Based Constraint Optimization Strategy
A systematic approach to solving placement optimization problems on spatial maps. This applies to any problem where you must place items on a grid to maximize an objective while respecting placement constraints.
Why Exhaustive Search Fails
Exhaustive search (brute-force enumeration of all possible placements) is the worst approach:
- Combinatorial explosion: Placing N items on M valid tiles = O(M^N) combinations
- Even small maps become intractable (e.g., 50 tiles, 5 items = 312 million combinations)
- Most combinations are clearly suboptimal or invalid
The Three-Phase Strategy
Phase 1: Prune the Search Space
Goal: Eliminate tiles that cannot contribute to a good solution.
Remove tiles that are:
- Invalid for any placement - Violate hard constraints (wrong terrain, out of range, blocked)
- Dominated - Another tile is strictly better in all respects
- Isolated - Too far from other valid tiles to form useful clusters
Before: 100 tiles in consideration
After pruning: 20-30 candidate tiles
This alone can reduce search space by 70-90%.
Phase 2: Identify High-Value Spots
Goal: Find tiles that offer exceptional value for your objective.
Score each remaining tile by:
- Intrinsic value - What does this tile contribute on its own?
- Adjacency potential - What bonuses from neighboring tiles?
- Cluster potential - Can this tile anchor a high-value group?
Rank tiles and identify the top candidates. These are your priority tiles - any good solution likely includes several of them.
Example scoring:
- Tile A: +4 base, +3 adjacency potential = 7 points (HIGH)
- Tile B: +1 base, +1 adjacency potential = 2 points (LOW)
Phase 3: Anchor Point Search
Goal: Find placements that capture as many high-value spots as possible.
- Select anchor candidates - Tiles that enable access to multiple high-value spots
- Expand from anchors - Greedily add placements that maximize marginal value
- Validate constraints - Ensure all placements satisfy requirements
- Local search - Try swapping/moving placements to improve the solution
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.
- 3d ago First seen · 111 lines · 35 tokens per session scan A 7d712d7dd4e6
map-optimization-strategy is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 967 once invoked, about $0.0002 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
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
llm-council
Query multiple LLM models in parallel from CodeAct and cross-reference their responses.
environment-discovery
Systematic exploration of unknown environments before starting work.
performant-code
Writing efficient code that handles large data and tight constraints.
Plan Mode
Clarify requirements and produce an implementation plan before changing files.