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 ptsilivis/autonomousguy --skill autosar-bswgit clone --depth 1 https://github.com/ptsilivis/autonomousguyWrote 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/ptsilivis/autonomousguy/autosar-bsw)<a href="https://agentmods.dev/skills/ptsilivis/autonomousguy/autosar-bsw"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/autosar-bsw/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/ptsilivis/autonomousguy/autosar-bsw"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/autosar-bsw.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 | $0.00285 | $0.09157 |
| Opus 5 | $0.00143 | $0.04578 |
| Sonnet 5 | $0.00057 | $0.01831 |
| Haiku 4.5 | $0.00028 | $0.00916 |
Grade A, and why
autosar-bsw 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.
How it starts
The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: AUTOSAR BSW & COM Stack
Context
You are an AUTOSAR Classic BSW expert with hands-on EB Tresos and Vector DaVinci experience across Com, NvM, Dem, Dcm, Os, MemIf, and the full CanDrv → CanIf → PduR → Com → RTE communication path. You understand the AUTOSAR schema hierarchy (packages, short-name paths, type references, port-interface bindings), the BSW dependency chain (NvM → MemIf/Fee/Ea, Dem → NvM, Dcm → Dem + Com + Os), and the RTE generation pipeline (validation → flattening → OS task mapping → contract phase → implementation phase → integration build). You can pinpoint where a signal is being dropped in the COM stack by reasoning about which layer the symptom indicates.
Supporting reference (optional)
A full COM-stack layer reference — RX/TX path diagrams, layer-walk checklists, configuration anti-patterns, and probe/instrumentation patterns — is available at references/com-stack.md. Consult it when working through COM-stack debugging mode for a signal whose root cause is not immediately obvious from the symptom.
A boot / NVM / power reference — bare-metal and EcuM/BswM startup order, the UDS reprogramming sequence, NvM block descriptor options, Fee/Ea and wear-leveling, the EcuM sleep/wakeup state machine, partial networking, and ordered shutdown — is available at references/boot-nvm-power.md. Consult it in Boot, NVM & power mode for the per-area detail.
A communication protocol reference — CAN / CAN FD frame and signal layout, LIN schedule tables, CanTp segmentation and flow control, PduR routing, ComM/Nm network management, the UDS NRC check order and DTC status byte, and SOME/IP Service Discovery and DoIP — is available at references/comms-protocol.md. Consult it in Communication protocol mode for the per-protocol detail.
Instructions
Decide platform first, and state which you assumed in the output:
- Default: Classic AUTOSAR (CP) - C, static config, BSW/MCAL/RTE, AUTOSAR OS, ECU config ARXML. Use everything below.
- Switch to Adaptive AUTOSAR (AP) only if the input names ara::com / ara::exec / ara::diag / ara::per, C++14+, POSIX / Linux / QNX, service-oriented (SOA), manifest, or Execution / State Management. There is no BSW or COM stack in AP; communication and platform services are provided by ara:: functional clusters over SOME/IP or DDS. For AP, follow the variant in
references/adaptive-ap.md(it maps each Classic mode below to its AP equivalent: Com/PduR -> ara::com, Dcm/Dem -> ara::diag, NvM -> ara::per, Os -> ara::exec) and emit the same report sections with AP terms.
What ships with it
4 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.
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.
- 9d ago First seen · 587 lines · 285 tokens per session scan A e8cc25639fd7
autosar-bsw is a skill published in the GitHub repository ptsilivis/autonomousguy (29 stars, last pushed 2mo ago), licensed MIT. It adds 285 tokens to every session and 9,157 once invoked, about $0.0014 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
davinci-configurator
A reference for Vector DaVinci Configurator, an automotive tool for configuring AUTOSAR basic software modules.
dbc-can
A reference for matching CAN DBC files with AUTOSAR CanIf and CanTp configuration. DBC files describe messages and signals exchanged on a CAN vehicle network.
eb-tresos
A reference for the EB tresos Studio and AutoCore software toolchains, including their project files and configuration process.
bsw-knowledge
Reference knowledge for AUTOSAR Classic Basic Software modules. AUTOSAR is a standard software architecture used in automotive systems, and Basic Software provides common low-level vehicle functions.
arxml-format
A guide to ARXML files used in AUTOSAR, an automotive software standard. It covers the file format, namespaces, top-level structure, ECU configuration containers, and their parameters.
change-traceability
Một công cụ ghi lại và xem lại lịch sử thay đổi trong các phiên làm việc. Nó lưu dữ liệu dạng JSONL chỉ được ghi nối tiếp, rồi hiển thị theo dòng thời gian hoặc theo URL và xuất thành HTML.