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 mohitmishra786/low-level-dev-skills --skill peripherals-from-datasheetgit clone --depth 1 https://github.com/mohitmishra786/low-level-dev-skillsWrote 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/mohitmishra786/low-level-dev-skills/peripherals-from-datasheet)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/peripherals-from-datasheet"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/peripherals-from-datasheet/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/mohitmishra786/low-level-dev-skills/peripherals-from-datasheet"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/peripherals-from-datasheet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 115 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00054 | $0.01068 |
| Opus 5 | $0.00027 | $0.00534 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
peripherals-from-datasheet 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 10d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peripherals from Datasheet
Purpose
Guide agents through a repeatable methodology for writing peripheral drivers from MCU reference manuals: locating register maps, interpreting bit definitions, following init sequences, respecting timing constraints, and producing maintainable register-level code. Pair with skills/baremetal/datasheet-and-refmanual-reading for doc-navigation methodology (kept as separate skills).
When to Use
- Starting a driver without vendor HAL
- Porting a peripheral between MCU families
- Verifying HAL behavior against the reference manual
- Debugging a peripheral that "should work" per examples
Workflow
1. Reference manual navigation
Typical RM structure
├── Memory map (peripheral base addresses)
├── Peripheral chapter (UART, SPI, GPIO, ...)
│ ├── Functional description
│ ├── Register map (table of offsets)
│ ├── Register bit definitions
│ └── Timing / electrical notes
└── Electrical characteristics (clock limits, setup/hold)
Start with the programming model section before copying register writes.
2. Extract register map
/* From RM — USART base 0x40004400 */
typedef struct {
volatile uint32_t SR; /* 0x00 status */
volatile uint32_t DR; /* 0x04 data */
volatile uint32_t BRR; /* 0x08 baud */
volatile uint32_t CR1; /* 0x0C control */
/* ... */
} USART_TypeDef;
#define USART2 ((USART_TypeDef *)0x40004400UL)
Verify offset column matches struct layout (padding for reserved words).
3. Init sequence checklist
Peripheral bring-up order
├── 1. Enable bus clock (RCC/APB/AHB register)
├── 2. Reset peripheral (if RM requires)
├── 3. Configure pins (GPIO alternate function)
├── 4. Configure peripheral registers (mode, baud, etc.)
├── 5. Enable peripheral (UE, TE, RE bits)
├── 6. Enable NVIC IRQ (if interrupt-driven)
└── 7. Verify status flags before first transaction
Bad — enable UART before clock:
USART2->CR1 |= USART_CR1_UE; /* USART clock still off — no effect */
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.
- 10d ago First seen · 134 lines · 54 tokens per session scan A 0e3e956ec175
peripherals-from-datasheet is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (198 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,068 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
fusion-360
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize Autodesk Fusion (Fusion 360), Python API (adsk.fusion), Parametric Timeline, and CAM toolpaths.
altium-designer
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize Altium Designer, DXP scripting engine, DRC rules, OutJob CAM generation, and high-speed PCB routing.
eartrumpet
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize EarTrumpet, Windows Core Audio APIs (WASAPI), pycaw audio session automation, and per-app endpoint routing.
codesys
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize CODESYS V3.5, IEC 61131-3 Structured Text (ST), ScriptEngine Python automation, EtherCAT/PROFINET, and OPC UA.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
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…