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 integral-action-designgit 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/integral-action-design)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/integral-action-design"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/integral-action-design/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/benchflow-ai/skillsbench/integral-action-design"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/integral-action-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00323 |
| Opus 5 | $0.00008 | $0.00161 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
integral-action-design 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:
- integral-action-design — 100% identical, 0 lines differ
What it actually says
Integral Action for Offset-Free Control
Why Integral Action?
MPC with model mismatch may have steady-state error. Integral action eliminates offset by accumulating error over time.
Implementation
u_I = gamma * u_I - c_I * dt * (T - T_ref)
u_total = u_mpc + u_I
Where:
- u_I: Integral control term
- gamma: Decay factor (0.9-0.99)
- c_I: Integral gain (0.1-0.5 for web systems)
- dt: Timestep
Tuning Guidelines
Integral gain c_I:
- Too low: Slow offset correction
- Too high: Oscillations, instability
- Start with 0.1-0.3
Decay factor gamma:
- gamma = 1.0: Pure integral (may wind up)
- gamma < 1.0: Leaky integrator (safer)
- Typical: 0.9-0.99
Anti-Windup
Limit integral term to prevent windup during saturation:
u_I = np.clip(u_I, -max_integral, max_integral)
For R2R Systems
Apply integral action per tension section:
for i in range(num_sections):
u_I[i] = gamma * u_I[i] - c_I * dt * (T[i] - T_ref[i])
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 · 51 lines · 16 tokens per session scan A e3368f03c7c5
integral-action-design is a skill published in the GitHub repository benchflow-ai/skillsbench (1,757 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 323 once invoked, about $0.0001 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
exploded-view-illustration
Techniques for drawing isometric or orthographic exploded-view hardware diagrams programmatically using Pillow, with annotation leader lines and layer separation.
membrowse-integrate
Integrate MemBrowse memory tracking into a project that produces ELF binaries. Use when the user wants to set up MemBrowse, add memory analysis GitHub workflows, create membrowse-targets.json for tracking memory usage, or add a MemBrowse badge to the README. Works with embedded firmware (STM32, ESP32, nRF, RISC-V) and…
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
akg-agents
An agent workflow for developing, generating, testing, and tuning AKG operators. AKG is a toolkit for generating optimized computational kernels.
fpga
FPGA development guidelines covering Vivado, SystemVerilog, timing closure, AXI interfaces, and hardware optimization.