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 Washabii14/agent-skills --skill automotive-embedded-skillsgit clone --depth 1 https://github.com/Washabii14/agent-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/washabii14/agent-skills/automotive-embedded-skills)<a href="https://agentmods.dev/skills/washabii14/agent-skills/automotive-embedded-skills"><img src="https://agentmods.dev/badge/skills/washabii14/agent-skills/automotive-embedded-skills/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/washabii14/agent-skills/automotive-embedded-skills"><img src="https://agentmods.dev/badge/skills/washabii14/agent-skills/automotive-embedded-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00123 | $0.04850 |
| Opus 5 | $0.00062 | $0.02425 |
| Sonnet 5 | $0.00025 | $0.00970 |
| Haiku 4.5 | $0.00012 | $0.00485 |
Grade A, and why
automotive-embedded-skills 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 12d 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Embedded C/C++/CAPL Best Practices
Comprehensive coding guidelines for automotive embedded software development in C, C++, and CAPL. Contains 180+ rules across 23 categories, prioritized by safety impact and industry compliance requirements (MISRA C:2012, MISRA C++:2023, AUTOSAR C++14 Classic & Adaptive, ISO 26262, ISO 21434). Covers full automotive communication stack (CAN/LIN/Ethernet/IP/TSN), cybersecurity, diagnostics, CAPL simulation/testing/fault injection, AUTOSAR BSW modules, boot/NVM/power management, compiler toolchains, static analysis tools, and CI/CD integration.
When to Apply
Reference these guidelines when:
- Writing new embedded C/C++ modules for automotive ECUs
- Implementing or reviewing CAN/LIN/Ethernet communication stacks
- Writing CAPL scripts for CANoe/CANalyzer simulation and testing
- Refactoring code for MISRA C/C++ or AUTOSAR C++14 compliance
- Designing safety-critical software (ASIL A-D per ISO 26262)
- Implementing RTOS task management and inter-task communication
- Reviewing code for memory safety, timing, and determinism
- Working with diagnostic protocols (UDS, OBD-II, DoIP)
- Implementing Automotive Ethernet (TCP, UDP, SOME/IP, DoIP, VLAN)
- Addressing cybersecurity requirements (ISO 21434, secure boot, TLS)
- Integrating with calibration/diagnostic tools (A2L, ODX, XCP)
- Optimizing for resource-constrained microcontrollers (RAM, Flash, CPU)
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Memory Safety & Management | CRITICAL | memory- |
| 2 | MISRA C/C++ Compliance | CRITICAL | misra- |
| 3 | AUTOSAR C++14 Guidelines (Classic & Adaptive) | CRITICAL | autosar- |
| 4 | Safety & Functional Safety (ISO 26262) | HIGH | safety- |
| 5 | Real-Time & Timing Constraints | HIGH | realtime- |
| 6 | Communication Protocols (CAN/LIN/Ethernet/IP/UDS) | HIGH | comm- |
| 7 | Concurrency & RTOS Patterns | MEDIUM-HIGH | rtos- |
| 8 | CAPL Scripting — CANoe | MEDIUM-HIGH | capl-canoe- |
| 9 | CAPL Scripting — vTESTstudio | MEDIUM-HIGH | capl-vtest- |
| 10 | Code Organization & Architecture | MEDIUM | arch- |
| 11 | Performance Optimization | MEDIUM | perf- |
| 12 | Build, Compilation & Static Analysis | MEDIUM | build- |
| 13 | Security & Cybersecurity (ISO 21434) | HIGH | security- |
| 14 | Testing & Verification | MEDIUM | test- |
| 15 | Tool Integration (A2L/ODX/FIBEX) | MEDIUM | integration- |
What ships with it
60 files 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.
- AGENTS.md 139 KB
- README.md 5.6 KB
- rules/_template.md 535 B
- rules/analysis-coverity.md 3.6 KB
- rules/analysis-cppcheck.md 4.2 KB
- rules/analysis-ldra.md 4.5 KB
- rules/analysis-parasoft.md 4.7 KB
- rules/analysis-pclint-config.md 3.9 KB
- rules/analysis-polyspace.md 4.7 KB
- rules/arch-callback-pattern.md 1.7 KB
- rules/arch-config-separation.md 1.8 KB
- rules/arch-hal-abstraction.md 1.4 KB
- rules/arch-layered-architecture.md 1.6 KB
- rules/arch-module-interface.md 1.7 KB
- rules/arch-state-machine.md 1.7 KB
- rules/autosar-adaptive-ara-com.md 6.0 KB
- rules/autosar-adaptive-ara-core.md 5.5 KB
- rules/autosar-adaptive-ara-diag.md 5.8 KB
- rules/autosar-adaptive-ara-exec.md 5.2 KB
- rules/autosar-adaptive-ara-log.md 5.0 KB
- rules/autosar-adaptive-ara-per.md 6.4 KB
- rules/autosar-adaptive-ara-phm.md 6.2 KB
- rules/autosar-braces-init.md 680 B
- rules/autosar-classic-bswm.md 3.8 KB
- rules/autosar-classic-canif-cantp.md 5.1 KB
- rules/autosar-classic-com.md 4.6 KB
- rules/autosar-classic-dcm-dem.md 5.1 KB
- rules/autosar-classic-ecum.md 3.6 KB
- rules/autosar-classic-nvm.md 5.6 KB
- rules/autosar-classic-os.md 5.6 KB
- rules/autosar-classic-pdu-router.md 3.8 KB
- rules/autosar-const-correctness.md 809 B
- rules/autosar-enum-class.md 768 B
- rules/autosar-no-exceptions-rt.md 910 B
- rules/autosar-no-unions.md 769 B
- rules/autosar-nodiscard.md 1009 B
- rules/autosar-override-final.md 889 B
- rules/autosar-smart-pointers.md 873 B
- rules/boot-autosar-adaptive-startup.md 5.3 KB
- rules/boot-autosar-classic-startup.md 3.4 KB
- rules/boot-baremetal-startup.md 3.5 KB
- rules/boot-bootloader-reprogramming.md 5.5 KB
- rules/boot-secure-boot-chain.md 6.2 KB
- rules/build-clang-analysis.md 4.2 KB
- rules/build-compiler-flags.md 1.1 KB
- rules/build-gcc-warnings.md 3.3 KB
- rules/build-greenhills-safety.md 3.9 KB
- rules/build-link-time-optimization.md 957 B
- rules/build-reproducible-builds.md 1.1 KB
- rules/build-static-analysis.md 1.0 KB
- rules/build-warnings-as-errors.md 874 B
- rules/capl-canoe-diagnostic-testing.md 1.7 KB
- rules/capl-canoe-environment-variables.md 1.4 KB
- rules/capl-canoe-error-frame-handling.md 1.5 KB
- rules/capl-canoe-gateway-routing.md 8.9 KB
- rules/capl-canoe-message-handler.md 1.0 KB
- rules/capl-canoe-multi-channel.md 5.9 KB
- rules/capl-canoe-node-simulation.md 1.8 KB
- rules/capl-canoe-rbs-cyclic.md 6.1 KB
- rules/capl-canoe-rbs-reactive.md 8.2 KB
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.
- 12d ago First seen · 338 lines · 123 tokens per session scan A 416048b18189
automotive-embedded-skills is a skill published in the GitHub repository Washabii14/agent-skills (10 stars, last pushed 6mo ago), licensed MIT. It adds 123 tokens to every session and 4,850 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
embedded-stm32
Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…
hip-kernel-optimization
This skill should be used when writing or tuning HIP kernels on AMD/NVIDIA GPUs, covering memory coalescing, shared-memory tiling, bank conflict avoidance, warp primitives, occupancy, vectorization, async ops, loop unrolling, and profiling.
cuda
Use when writing CUDA kernels, managing the thread, block, and grid hierarchy, tiling shared memory, using streams, setting nvcc flags, or using Thrust. Not for kernel debugging: use cuda-debugging.
acad-arx-wizard
Agentic ObjectARX project scaffolding for AutoCAD 2027 / Visual Studio 2026. Replaces the broken .vsz VsWizardEngine wizard with a PowerShell script that generates identical C++ project files. Works for new ARX/DBX/CRX projects and add-on class wizards (Jig, Reactors, Custom Object, MFC, .NET Wrapper, COM Wrapper…
hls-c2rtl
Translate C / C++ / SystemC algorithmic descriptions into synthesizable RTL via High-Level Synthesis. Use when the user says "HLS", "C to RTL", "C++ to Verilog", "Vitis HLS", "Catapult", "XLS", "algorithmic design", or provides a reference implementation in software and asks for hardware.