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 5.5 | $0.00049 | $0.01940 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (16 stars, last pushed 8mo ago), licensed MIT. It adds 123 tokens to every session and 4,850 once invoked, about $0.0005 per session on Opus 5.5. 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.
automotive-embedded-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| automotive-embedded-skillsWashabii14/agent-skills | Skill | 16 | 8mo ago | MIT | A | 123 | Claude Code, Codex |
| doca-argpNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 277 | Claude Code, Codex |
| holoscan-module-lifecycleNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| embedded-stm32Mindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 87 | Claude Code |
| embedded-firmware-devAmethystLuna/embedded-workbench | Skill | 30 | yesterday | MIT | A | 59 | Claude Code |
| hls-c2rtlvibeic/vibe-ic | Skill | 32 | today | Apache-2.0 | A | 79 | Claude Code |
| hip-kernel-optimizationAMD-AGI/Apex | Skill | 78 | 1mo ago | MIT | A | 56 | Claude Code, Codex |