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-treegit 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-tree)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/device-tree"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/device-tree/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-tree"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/device-tree.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 | $0.00038 | $0.01457 |
| Opus 5 | $0.00019 | $0.00728 |
| Sonnet 5 | $0.00008 | $0.00291 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
device-tree 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Device tree
Contract
| Field | Bound contract |
|---|---|
| Trigger | Writing or debugging Linux devicetree source: DTS/DTSI structure, bindings, phandles, overlays, compatible and property layout, or a driver whose OF probe never fires. |
| Authority | Read-only. Writes nothing. Chat output only. No remote mutation. |
| Side effect | Returns DTS fragments, property tables, and debug commands. No source files are modified. |
| Done | The node or fragment, the property set with cells explained, and a probe-failure diagnosis are delivered. |
Inputs
- Hardware fact to describe (required): the block or device, its MMIO base, IRQ, clocks, and the bus it sits on.
- Board context (optional): the SoC
.dtsito include and the board.dtsto extend. - Failure report (optional): the symptom, such as a driver that never probes or an IRQ that never fires.
Procedure
-
Lay out the node under its bus parent. A board file includes the SoC
.dtsiand extends or references its nodes by label./dts-v1/; #include "soc.dtsi" / { model = "My Board"; compatible = "vendor,my-board", "vendor,soc-family"; &uart0 { status = "okay"; }; };uart0: serial@40011000 { compatible = "vendor,uart"; reg = <0x40011000 0x400>; interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk_uart0>; status = "disabled"; /* the board file sets "okay" */ };Done when: the node sits under the right bus parent and every cell count matches the parent's
#address-cellsand#size-cells. -
Set the load-bearing properties correctly.
Property Meaning compatibleDriver match strings, most specific first regMMIO address and length, cells per #address-cells/#size-cellsinterruptsIRQ specifier, cells defined by the interrupt parent clocks/clock-namesPhandles to clock providers status"disabled"keeps the device unprobed
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 · 114 lines · 38 tokens per session scan A 8f0482604bb7
device-tree is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,457 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 2026-09-06.
Other skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
evpn-vxlan-fabric
EVPN/VXLAN fabric audit and troubleshooting — VTEPs, VNIs, route types, multihoming, underlay/overlay validation. Use when troubleshooting VXLAN overlay reachability, auditing leaf-spine fabric health, debugging silent hosts or asymmetric flooding, or validating anycast gateway and ESI multihoming state.
triaging-robot-logs
Use when investigating a robot log or flight log with bagel — finding events, anomalies, or "what happened around X" in rosbags, MCAP, CAN, MDF4, ULog, or Betaflight files. Routes to the server's triage capability.
yam-robot-debugging
Use for YAM real-robot debugging: saved-script edits, physical runs, artifact inspection, autonomous patch-and-retry loops, and compact runtime context updates.
diagnose-hid-keycodes
Find out what an unknown USB/Bluetooth HID button actually emits without assuming the label or documentation. Uses Karabiner's.