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 datasheet-and-refmanual-readinggit 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/datasheet-and-refmanual-reading)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/datasheet-and-refmanual-reading"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/datasheet-and-refmanual-reading/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/datasheet-and-refmanual-reading"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/datasheet-and-refmanual-reading.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 | $0.00048 | $0.01228 |
| Opus 5 | $0.00024 | $0.00614 |
| Sonnet 5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
datasheet-and-refmanual-reading 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Datasheet and reference manual reading
Contract
| Field | Bound contract |
|---|---|
| Trigger | Driver work starts on unfamiliar silicon, a register bit behaves ambiguously, an electrical or timing limit must be confirmed, or the question is where in the documentation a fact lives. |
| Authority | Read-only: reads vendor documents and reports locations, extracted values, and cross-references to chat. Rollback is not needed because no file is written. No remote mutation. |
| Side effect | Chat output only. |
| Done | Each requested fact is reported with the document, section, and table it came from, its conditions (voltage range, silicon revision, mode) are stated, and the errata sheet has been checked for the peripheral. |
Inputs
- The exact part number, including package and revision suffix, and the silicon revision if known (
DBGMCU->IDCODEREV_IDon STM32). - The vendor documents: datasheet, reference manual, core programming manual, and errata sheet.
- The question: a pin, a register field, a clock limit, a timing parameter, or a peripheral behavior.
Procedure
-
Pick the document by the kind of fact. Done when: the fact is being sought in the document that owns it.
Document Owns Datasheet Pinout and alternate-function table, absolute maximum ratings, operating conditions, package, electrical and timing characteristics Reference manual Memory map, register maps and bit fields, clock tree, peripheral behavior and init sequences Core programming manual (Arm) Core registers, NVIC, SysTick, MPU, fault registers, debug Errata sheet Silicon defects and the firmware workaround for each The datasheet says what exists; the reference manual says how to program it.
-
Read the reference manual in this order on a first pass: memory and bus architecture, reset and clock control, GPIO and pin multiplexing, the target peripheral chapter, the interrupt and event mapping table, then electrical characteristics only when timing is critical. Done when: the base address, clock enable bit, pin mux, and interrupt line for the peripheral are each located.
-
Extract each register with its full row, not just the bit name. Done when: every column below is filled for each register the driver will touch.
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 · 73 lines · 48 tokens per session scan A 42cb5c7699f8
datasheet-and-refmanual-reading is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,228 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.