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/simulation-metricsnpx skills add benchflow-ai/skillsbench --skill simulation-metricsgit 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/simulation-metrics)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/simulation-metrics"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/simulation-metrics.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 | $0.00034 | $0.00546 |
| Opus 5 | $0.00017 | $0.00273 |
| Sonnet 5 | $0.00007 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
simulation-metrics 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 6d 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:
- simulation-metrics — 100% identical, 0 lines differ
What it actually says
Control System Performance Metrics
Rise Time
Time for system to go from 10% to 90% of target value.
def rise_time(times, values, target):
"""Calculate rise time (10% to 90% of target)."""
t10 = t90 = None
for t, v in zip(times, values):
if t10 is None and v >= 0.1 * target:
t10 = t
if t90 is None and v >= 0.9 * target:
t90 = t
break
if t10 is not None and t90 is not None:
return t90 - t10
return None
Overshoot
How much response exceeds target, as percentage.
def overshoot_percent(values, target):
"""Calculate overshoot percentage."""
max_val = max(values)
if max_val <= target:
return 0.0
return ((max_val - target) / target) * 100
Steady-State Error
Difference between target and final settled value.
def steady_state_error(values, target, final_fraction=0.1):
"""Calculate steady-state error using final portion of data."""
n = len(values)
start = int(n * (1 - final_fraction))
final_avg = sum(values[start:]) / len(values[start:])
return abs(target - final_avg)
Settling Time
Time to stay within tolerance band of target.
def settling_time(times, values, target, tolerance=0.02):
"""Time to settle within tolerance of target."""
band = target * tolerance
lower, upper = target - band, target + band
settled_at = None
for t, v in zip(times, values):
if v < lower or v > upper:
settled_at = None
elif settled_at is None:
settled_at = t
return settled_at
Usage
times = [row['time'] for row in results]
values = [row['value'] for row in results]
target = 30.0
print(f"Rise time: {rise_time(times, values, target)}")
print(f"Overshoot: {overshoot_percent(values, target)}%")
print(f"SS Error: {steady_state_error(values, target)}")
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.
- 6d ago First seen · 86 lines · 34 tokens per session scan A 9e145fd19a2c
simulation-metrics is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 546 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 2026-08-30.
Other skills, from other repositories
run-aeon-benchmark
Use when asked to run, benchmark, evaluate, or score an LLM with AEON Bench. You run the AEON Bench Pod on the user's machine, point it at a model, run the benchmark, and submit the signed result to the public leaderboard at aeon-bench.com. All work happens on the pod. The mothership only shows the board and accepts…
plate-tectonics-geospatial
Analyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to boundaries.
data-matching
Matching observation data to simulation output with exact datetime and depth binning.
model-calibration
Calculating RMSE metrics and parameter calibration for lake model validation.
dbscan-custom-metric
Run DBSCAN clustering with a custom distance metric using sklearn, including how to define weighted Euclidean metrics and extract cluster centroids.
greedy-bipartite-matching
Implement greedy bipartite matching for pairing cluster centroids with expert annotations.