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 skills add benchflow-ai/skillsbench --skill hex-grid-spatialgit 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/hex-grid-spatial)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/hex-grid-spatial"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/hex-grid-spatial.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00940 |
| Opus 5 | $0.00017 | $0.00470 |
| Sonnet 5 | $0.00007 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
hex-grid-spatial 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 4d 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:
- hex-grid-spatial — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hex Grid Spatial Utilities
Utilities for hexagonal grid coordinate systems using odd-r offset coordinates (odd rows shifted right).
Coordinate System
- Tile 0 is at bottom-left
- X increases rightward (columns)
- Y increases upward (rows)
- Odd rows (y % 2 == 1) are shifted right by half a hex
Direction Indices
2 1
\ /
3 - * - 0
/ \
4 5
0=East, 1=NE, 2=NW, 3=West, 4=SW, 5=SE
Core Functions
Get Neighbors
def get_neighbors(x: int, y: int) -> List[Tuple[int, int]]:
"""Get all 6 neighboring hex coordinates."""
if y % 2 == 0: # even row
directions = [(1,0), (0,-1), (-1,-1), (-1,0), (-1,1), (0,1)]
else: # odd row - shifted right
directions = [(1,0), (1,-1), (0,-1), (-1,0), (0,1), (1,1)]
return [(x + dx, y + dy) for dx, dy in directions]
Hex Distance
def hex_distance(x1: int, y1: int, x2: int, y2: int) -> int:
"""Calculate hex distance using cube coordinate conversion."""
def offset_to_cube(col, row):
cx = col - (row - (row & 1)) // 2
cz = row
cy = -cx - cz
return cx, cy, cz
cx1, cy1, cz1 = offset_to_cube(x1, y1)
cx2, cy2, cz2 = offset_to_cube(x2, y2)
return (abs(cx1-cx2) + abs(cy1-cy2) + abs(cz1-cz2)) // 2
Tiles in Range
def get_tiles_in_range(x: int, y: int, radius: int) -> List[Tuple[int, int]]:
"""Get all tiles within radius (excluding center)."""
tiles = []
for dx in range(-radius, radius + 1):
for dy in range(-radius, radius + 1):
nx, ny = x + dx, y + dy
if (nx, ny) != (x, y) and hex_distance(x, y, nx, ny) <= radius:
tiles.append((nx, ny))
return tiles
Usage Examples
# Find neighbors of tile (21, 13)
neighbors = get_neighbors(21, 13)
# For odd row: [(22,13), (22,12), (21,12), (20,13), (21,14), (22,14)]
# Calculate distance
dist = hex_distance(21, 13, 24, 13) # Returns 3
# Check adjacency
is_adj = hex_distance(21, 13, 21, 14) == 1 # True
# Get all tiles within 3 of city center
workable = get_tiles_in_range(21, 13, 3)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 102 lines · 35 tokens per session scan A 3370ef7f3f47
hex-grid-spatial is a skill published in the GitHub repository benchflow-ai/skillsbench (1,754 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 940 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
agora-dungeon-game-dev
Build a 2D dungeon game where AI agents cooperate, work on businesses, and an orchestrator (human) guides them — Phaser 3 + TypeScript + React + Node backend with LLM agents.
arc-skill
Solve an interactive hidden-rule ARC-AGI-3 game from its game ID. Contains the complete playing doctrine (predict before every action, graded claims, one-page notes, optional executable-rules search) plus the arc harness the agent drives. Use whenever asked to solve, play, or continue an ARC-AGI-3 game.
dialogue-graph
A library for building, validating, visualizing, and serializing dialogue graphs. Use this when parsing scripts or creating branching narrative structures.
dialogue-graph
A library for building, validating, visualizing, and serializing dialogue graphs. Use this when parsing scripts or creating branching narrative structures.
unreal-mcp
Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a .uproject…
unreal-game-builder
Use when building, completing, or repairing a playable Unreal Engine game or vertical slice that spans several gameplay, world, presentation, testing, and delivery domains.