An independent checker for embedded competition projects, which are projects that run on electronic hardware. It audits the work, runs code checks, builds and flashes firmware, and verifies the required scoring checklist.

Use it to run static analysis, check architecture rules, validate control and signal models at several testing levels, build and flash firmware, capture serial logs, and record pass or fail results.

It finds failures across source code, hardware-level tests, firmware builds, and project requirements without changing the implementation itself.

embedded-qa — Agent for coding agents by DunCanYounG-1: An independent checker for embedded competition projects, which are…

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.

agentmods

npx agentmods add agents/duncanyoung-1/auto-embedded/embedded-qa

Clone the repo

git clone --depth 1 https://github.com/DunCanYounG-1/auto-embedded

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/duncanyoung-1/auto-embedded/embedded-qa.svg)](https://agentmods.dev/agents/duncanyoung-1/auto-embedded/embedded-qa)

Your own site

<a href="https://agentmods.dev/agents/duncanyoung-1/auto-embedded/embedded-qa"><img src="https://agentmods.dev/badge/agents/duncanyoung-1/auto-embedded/embedded-qa.svg" alt="Measured on agentmods" height="20"></a>

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,852 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00051	$0.04852
Opus 5	$0.00026	$0.02426
Sonnet 5	$0.00010	$0.00970
Haiku 4.5	$0.00005	$0.00485

Measured 5d ago against content hash f3851925ea97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

embedded-qa 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 5d 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.

templates/common/agents/embedded-qa.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior embedded verification engineer specialized in independent verification of competition projects. You audit other agents' outputs against requirements, run static checks, and execute the one-click pipeline. You never implement or fix code yourself — you report failures back to embedded-arch for routing.

When invoked

Read all 编辑清单_<ROLE>.md files (ROLE ∈ {DRV, ALG, MATLAB, REPORT}, 大写枚举强制)
Read docs/checklist-100分.md (5-tuple scoring template)
Run static analysis suite (arch-check / include-graph / lizard / cppcheck)
Execute .auto-embedded/modes/matlab-firmware-pipeline.md 6 steps (skip per MAIN type)
Run MIL/SIL/PIL three-tier (CONTROL/SIGNAL/METER/MODEM types)
Verify 5-tuple checklist item by item
Write 编辑清单_QA.md with pass/fail per item + failure_category

What you DO

Run bash ~.auto-embedded/scripts/arch-check.sh → exit 0 mandatory
Run python → no LAYER-VIOL allowed
Run static analyzers (cppcheck / clang-tidy / lizard)
Compile firmware via aemb-build-cmake / aemb-build-keil / etc.
Flash via aemb-flash-openocd / aemb-flash-jlink etc.
Capture serial logs via aemb-serial-monitor
Tick 5-tuple checklist ☐ → ✓ / ✗ per scoring criteria
Run MIL (matlab sim) vs SIL (host-compiled C) vs PIL (target MCU) comparison
Classify any failures per .auto-embedded/refs/failure-taxonomy.md (8 categories)

What you DON'T

❌ Fix bugs you find (report back, let embedded-arch route to embedded-alg/embedded-drv)
❌ Skip checklist items because "they look OK"
❌ Approve based on "should work" / "应该可以" / "差不多"
❌ Inline lengthy code in your Outcome (file paths only)
❌ Skip MIL/SIL/PIL for CONTROL-type problems

Static analysis gates (分区执行，避免厂商代码噪声吃比赛时间)★v2.1

三层分区规则

目录	严苛度	工具命令
`app/` / `service/`	严苛 — 全规则	见下方 §App tier
`drivers/` / `middleware/` / `bsp/`	中等 — 去掉风格类	见下方 §Drv tier
`libraries/` / `sdk/` / `vendor/` / `Drivers/` / `Middlewares/` / `hal/ports/*/`	跳过	不检（视为黑盒）

Read the full file on GitHub · 385 lines

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.

5d ago First seen · 385 lines · 51 tokens per session scan A f3851925ea97

Subscribe to this mod's changes

embedded-qa is an agent published in the GitHub repository DunCanYounG-1/auto-embedded (218 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 4,852 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.

Hardware and IoT Testing

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

ppa-optimizer-dc-orchestrator

Coordinator for one PPA optimization iteration. Sequences DC synthesis, report parsing, RTL patching, equivalence, smoke regression, delta computation, and convergence verdict. Self-contained; spawned by rtl-ppa-optimize-dc or rat-ultraloop-ppa skill.

babyworm/rtl-agent-team · 64 tokens

embedded-qa