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 geospatial-routing-datagit 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/geospatial-routing-data)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/geospatial-routing-data"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/geospatial-routing-data.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 | $0.00065 | $0.01416 |
| Opus 5 | $0.00032 | $0.00708 |
| Sonnet 5 | $0.00013 | $0.00283 |
| Haiku 4.5 | $0.00006 | $0.00142 |
Grade A, and why
geospatial-routing-data 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 8d 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
3 near-identical copies found in the catalogue:
- geospatial-routing-data — 100% identical, 0 lines differ
- geospatial-routing-data — 100% identical, 0 lines differ
- geospatial-routing-data — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geospatial Routing Data
Use this skill before building a routing model or validating a routing report that contains coordinates, depots, station IDs, and route sequences.
The main risk is mixing user-facing IDs with internal array indices or using a different distance metric from the task.
Parse Data Safely
Load structured data with a parser and build explicit mappings:
import json
from pathlib import Path
data = json.loads(Path("/root/data.json").read_text())
stations_data = data["stations"]
station_ids = [int(s["id"]) for s in stations_data]
if len(station_ids) != len(set(station_ids)):
raise ValueError("duplicate station ids")
id_to_idx = {sid: idx for idx, sid in enumerate(station_ids)}
idx_to_id = {idx: sid for sid, idx in id_to_idx.items()}
Use internal indices in optimization variables. Use original station IDs in final reports.
Coordinate Validation
Check coordinates before building distances:
def parse_location(record, label):
lat = float(record["latitude"])
lon = float(record["longitude"])
if not (-90.0 <= lat <= 90.0):
raise ValueError(f"{label} latitude out of range: {lat}")
if not (-180.0 <= lon <= 180.0):
raise ValueError(f"{label} longitude out of range: {lon}")
return {"latitude": lat, "longitude": lon}
depot = parse_location(data["depot"], "depot")
station_locations = [parse_location(s, f"station {s['id']}") for s in stations_data]
Latitude and longitude are degrees. Convert to radians only inside the distance function.
Great-Circle Distance
Match the task's declared distance metric. If the task specifies an Earth radius, use that exact value.
For great-circle miles with Earth radius 3960.0, use:
import math
def great_circle_miles(a, b, radius=3960.0):
lat1 = float(a["latitude"])
lon1 = float(a["longitude"])
lat2 = float(b["latitude"])
lon2 = float(b["longitude"])
deg_to_rad = math.pi / 180.0
phi1 = (90.0 - lat1) * deg_to_rad
phi2 = (90.0 - lat2) * deg_to_rad
theta1 = lon1 * deg_to_rad
theta2 = lon2 * deg_to_rad
cos_arc = (
math.sin(phi1) * math.sin(phi2) * math.cos(theta1 - theta2)
+ math.cos(phi1) * math.cos(phi2)
)
cos_arc = max(-1.0, min(1.0, cos_arc))
return math.acos(cos_arc) * radius
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.
- 8d ago First seen · 207 lines · 65 tokens per session scan A 0e278fce8dbf
geospatial-routing-data is a skill published in the GitHub repository benchflow-ai/skillsbench (1,748 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,416 once invoked, about $0.0003 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 2026-08-30.
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.