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 adc-dac-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/adc-dac-baremetal)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/adc-dac-baremetal"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/adc-dac-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/adc-dac-baremetal"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/adc-dac-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 | $0.00043 | $0.01619 |
| Opus 5 | $0.00022 | $0.00809 |
| Sonnet 5 | $0.00009 | $0.00324 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
adc-dac-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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADC and DAC on bare metal
Contract
| Field | Bound contract |
|---|---|
| Trigger | The task is to sample an analog input, run the ADC continuously into a DMA buffer, calibrate the ADC after reset, or drive a DAC channel on an MCU without a vendor HAL. |
| Authority | Read-only: emits register sequences, formulas, and diagnostics to chat; the user pastes them into their firmware. Rollback is not needed because no file is written. No remote mutation. |
| Side effect | Chat output only. |
| Done | The guidance names the clock enable, pin mode, sampling time, calibration step, trigger, and readout for the target family, and every register bit is cited to the reference manual chapter it comes from. |
Inputs
- Target MCU family and part number (STM32F1, STM32F4, STM32G4, STM32L4, or another family with a reference manual at hand).
- The analog pin and ADC channel, from the datasheet pin table.
- Sample rate and source impedance of the signal.
- Whether readout is polled, interrupt-driven, or DMA circular.
- The ADC clock frequency after prescaling, from the clock tree.
Procedure
-
Enable the ADC and GPIO clocks and put the pin in analog mode. The ADC reads nothing from a pin still in digital input mode. Done when: the RCC enable bit for the ADC bus and the GPIO port are set and
MODERfor the pin reads analog (11). -
Power the ADC on and wait the stabilization time the datasheet gives as
tSTAB. On STM32F4 this isADC_CR2_ADONfollowed by a short wait; the wait is a datasheet number, not a magic loop count. Done when:ADONis set and the wait matches the datasheet value for the ADC clock in use.RCC->APB2ENR |= RCC_APB2ENR_ADC1EN; ADC1->CR2 |= ADC_CR2_ADON; delay_us(ADC_TSTAB_US); /* tSTAB from the datasheet, not a guessed loop */ -
Calibrate where the family requires it. STM32F1 exposes
ADC_CR2_RSTCALthenADC_CR2_CALinCR2and the firmware polls each bit until hardware clears it. STM32L4 and STM32G4 exposeADCALinADC_CRwith the ADC disabled. STM32F4 has no software calibration step; the part is factory calibrated. Done when: the family's calibration sequence has run, or the reference manual confirms the family has none. -
Set the sampling time from the datasheet graph of sampling time against source impedance. On STM32F4
SMPR2fieldSMP0value100(ADC_SMPR2_SMP0_2) selects 84 ADC clock cycles for channel 0; the other encodings are 3, 15, 28, 56, 112, 144, and 480 cycles. A high-impedance source needs the longer settings. Done when: the chosen sampling time covers the source impedance at the ADC clock in use. -
Select the channel sequence and start one conversion, then poll end-of-conversion and read the data register. Done when: a polled single conversion returns a plausible value for a known input (mid-rail or ground).
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 · 81 lines · 43 tokens per session scan A a65be99d51e2
adc-dac-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 43 tokens to every session and 1,619 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
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.