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 OutlineDriven/outline-driven-development --skill device-driversgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/device-drivers)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/device-drivers"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/device-drivers/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/outlinedriven/outline-driven-development/device-drivers"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/device-drivers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 98 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 98 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00046 | $0.01868 |
| Opus 5 | $0.00023 | $0.00934 |
| Sonnet 5 | $0.00009 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade B, and why
device-drivers scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo udevadm control --reload-rules && sudo udevadm trigger How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Device drivers
Contract
| Field | Bound contract |
|---|---|
| Trigger | Writing or debugging a Linux device driver: platform_driver, i2c_driver, or spi_driver probe and remove, char device read/write/ioctl, threaded IRQs, coherent or streaming DMA, regmap, runtime power management, or udev node permissions. |
| Authority | Reversible local: writes only driver source, Kconfig and Makefile entries, and udev rule files inside the project tree; rollback is version control. No remote mutation. |
| Side effect | Local edits to driver source, Kconfig and Makefile entries, and udev rules; guidance to chat. |
| Done | The driver probes and unbinds cleanly, IRQ, DMA, and PM paths use the correct APIs, and every observed symptom maps to one checked cause. |
Inputs
- Driver code or symptom (required): source under review, a probe failure, an IRQ storm, a missing
/devnode, or DMA corruption. - Bus and device origin (optional):
platform,i2c, orspi; the device treecompatiblestring or ACPI id. - Kernel version (optional): mainline 7.2 or LTS 6.18 assumed when not stated.
- Register map or datasheet (optional): needed for the regmap layout and PM sequencing.
Procedure
-
Name the bus, the device origin, and the kernel. Confirm the device comes from device tree, ACPI, or a legacy board file, and read
uname -ron the target. Done when: the bus, the origin, and the kernel version are recorded. -
Build probe and remove around managed resources. Remap the memory region with
devm_platform_ioremap_resource, stash state withplatform_set_drvdata, and register withmodule_platform_driver. Keepremoveempty when every resource isdevm_*-managed.static int my_probe(struct platform_device *pdev) { void __iomem *base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); platform_set_drvdata(pdev, ctx); return 0; } static struct platform_driver my_driver = { .probe = my_probe, .remove = my_remove, .driver = { .name = "my-device" }, }; module_platform_driver(my_driver);
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.
- 3d ago First seen · 128 lines · 46 tokens per session scan B 52b207c2863b
device-drivers is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,868 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
automatic-cybernetic-flow-design
Use when the user wants a cybernetic flow design document for an interactive system. Specifies sensors, actuators, feedback paths, delays, and oscillation risk, and writes the design to a named local file. Not for implementing or deploying the system.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
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…
mi300-hip-vs-nvidia
MI300 HIP programming differences vs NVIDIA—wavefront vs warp, memory hierarchy, MFMA usage, occupancy, and profiling pitfalls.
gpu-memory-model
GPU memory model skill for SIMT execution and memory hierarchy. Use when analyzing warp divergence, memory coalescing, shared memory bank conflicts, cache behavior, atomics, or occupancy tradeoffs. Activates on queries about SIMT, warp coalescing, bank conflicts, wavefront, GPU occupancy, or memory-bound kernels.
ios-build-cleanup
Use when the user wants a clean Xcode rebuild by deleting DerivedData and build artifacts. Do not use for diagnosing a specific build error: use ios-build-fix.