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 dma-baremetalgit 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/dma-baremetal)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/dma-baremetal"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/dma-baremetal/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/dma-baremetal"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/dma-baremetal.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 | $0.00044 | $0.01772 |
| Opus 5 | $0.00022 | $0.00886 |
| Sonnet 5 | $0.00009 | $0.00354 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
dma-baremetal 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DMA on bare metal
Contract
| Field | Bound contract |
|---|---|
| Trigger | A UART, SPI, or ADC transfer must run without the CPU, an audio or sensor stream needs a double buffer, or a DMA transfer does not start or delivers corrupt data. |
| Authority | Read-only: emits stream configuration, interrupt handling, and cache-maintenance sequences to chat; the user places them in the firmware. Rollback is not needed because no file is written. No remote mutation. |
| Side effect | Chat output only. |
| Done | The stream and channel (or request line) are named from the reference manual request table, the register sequence configures the stream before enabling it, the interrupt handler clears the right flag register, and cache maintenance is stated for cores with a data cache. |
Inputs
- Target part and DMA controller type (STM32F4 stream and channel matrix, STM32L4 channel and request selection, STM32G0/G4/H7 DMAMUX, or another controller with its request table).
- Direction: peripheral to memory, memory to peripheral, or memory to memory.
- Peripheral data register address and data width.
- Buffer address, length, and whether the buffer is single, circular, or double.
- Whether the core has a data cache (Cortex-M7) and where the buffer lives.
Procedure
- Find the request mapping. On STM32F4 each peripheral request is fixed to a stream and channel pair in the DMA chapter's request table; USART2 RX is DMA1 Stream 5, Channel 4, and ADC1 is DMA2 Stream 0 or Stream 4, Channel 0. On DMAMUX parts the request is a number written to the mux channel. Done when: the stream and channel or request number are quoted from the table.
- Enable the DMA controller clock, make sure the stream is disabled, and configure it: peripheral address, memory address, count, direction, data sizes, memory increment, and interrupt enables. Set
ENin a separate write after configuration; a stream still enabled ignores configuration writes. Done when:ENreads 0 before configuration and 1 after the final write.
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 · 95 lines · 44 tokens per session scan A b7cd3ee228bf
dma-baremetal is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,772 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.