autosar-swc

autosar-swc is a skill for Claude Code, Codex from ptsilivis/autonomousguy. It costs 240 tokens per session (6,288 once invoked), scanned A, original, MIT.

A specialist guide for designing AUTOSAR Classic software components, the units of application code that communicate through the Runtime Environment (RTE).

In plain words
What is it for?
Use it to design software-component structures, define sender-receiver or client-server interfaces, specify runnables and protected sections, and review ARXML or RTE-based implementations.
Why use it?
It helps turn a feature into correctly connected components, interfaces, events, and C code that fit the AUTOSAR model.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design software-component structures, define sender-receiver or client-server interfaces, specify runnables and protected sections, and review ARXML or RTE-based implementations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ptsilivis/autonomousguy/autosar-swc
Install

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.

Any agent
npx skills add ptsilivis/autonomousguy --skill autosar-swc
Clone the repo
git clone --depth 1 https://github.com/ptsilivis/autonomousguy

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for autosar-swc

README.md
[![agentmods](https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/autosar-swc/github.svg)](https://agentmods.dev/skills/ptsilivis/autonomousguy/autosar-swc)
Your own site
<a href="https://agentmods.dev/skills/ptsilivis/autonomousguy/autosar-swc"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/autosar-swc/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.

agentmods 80×15 button for autosar-swc

Your own site · 80×15
<a href="https://agentmods.dev/skills/ptsilivis/autonomousguy/autosar-swc"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/autosar-swc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 240 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00240 $0.06288
Opus 5 $0.00120 $0.03144
Sonnet 5 $0.00048 $0.01258
Haiku 4.5 $0.00024 $0.00629

Measured 9d ago against content hash f3af401bbe7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autosar-swc 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 9d 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.

skills/autosar/autosar-swc/SKILL.md · 532 lines

How it starts

The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: AUTOSAR SWC Design & Development

Context

You are an AUTOSAR Classic Platform system architect and developer with end-to-end experience from feature decomposition through ARXML modelling, C implementation, and integration review. You design SWC topologies, specify port interfaces with semantically correct ComSpecs, write production-ready SWC skeletons with correct RTE API usage, sketch architecture diagrams as plain-text box-and-arrow notation (no Mermaid / PlantUML dependency — the diagrams render identically in every viewer and in raw text), and audit existing SWC code for compliance with AUTOSAR Classic methodology, MCAL abstraction, and platform data-type rules. Toolchains: EB Tresos (TargetLink + RTE Generator) and Vector DaVinci Developer.

Supporting reference (optional)

A full RTE API / port-interface / runnable-event / data-type reference is at references/rte-api.md. Consult it when:

  • You need the canonical name for an RTE API variant (Read vs IRead, Call vs Result, etc.).
  • You need to choose between activation events (TimingEvent vs DataReceivedEvent vs SwcModeSwitchEvent).
  • You need the AUTOSAR platform type vs C99 <stdint.h> quick lookup.
  • You need the ARXML element name for a specific concept (composition, connector, ExclusiveArea, etc.).

Instructions

Decide platform first, and state which you assumed in the output:

  • Default: Classic AUTOSAR (CP) - SWCs, RTE, ARXML, runnables, static config, C, AUTOSAR OS. Use everything below.
  • Switch to Adaptive AUTOSAR (AP) only if the input names ara::com / ara::exec, C++14+, POSIX / Linux / QNX, service-oriented (SOA), manifest, proxy/skeleton, or Adaptive Application. In AP there are no SWCs, ports, runnables, or RTE; you design Adaptive Applications that offer/consume ara::com service interfaces (events/methods/fields) with skeleton (provider) and proxy (consumer). For AP, follow the variant in references/adaptive-ap.md, which maps each Classic mode below to its AP equivalent, and emit the same report sections with AP terms.

Read the full file on GitHub · 532 lines

Files

What ships with it

2 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.

Changes

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.

  1. 9d ago First seen · 532 lines · 240 tokens per session scan A f3af401bbe7b

Subscribe to this mod's changes

autosar-swc is a skill published in the GitHub repository ptsilivis/autonomousguy (29 stars, last pushed 2mo ago), licensed MIT. It adds 240 tokens to every session and 6,288 once invoked, about $0.0012 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.