What is embedded-alg?

An embedded-software coding assistant for application layers such as state machines, command-line parsers, control logic, signal codecs, and file-system services. It uses existing drivers and generated control coefficients without accessing hardware registers directly.

Use it to build embedded competition features such as control loops, command parsers, configuration, logging, file-system glue, and startup orchestration. It can also connect application code to outputs from driver, control-design, and vision tools.

It keeps application code separate from low-level hardware code, reducing the risk of reimplementing drivers or using hardware details in the wrong layer. It also gives the project a defined place for service logic and main program coordination.

embedded-alg — Agent for coding agents by DunCanYounG-1: An embedded-software coding assistant for application layers such as…

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-alg

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-alg.svg)](https://agentmods.dev/agents/duncanyoung-1/auto-embedded/embedded-alg)

Your own site

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

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,890 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	$0.00059	$0.01890
Opus 5	$0.00030	$0.00945
Sonnet 5	$0.00012	$0.00378
Haiku 4.5	$0.00006	$0.00189

Measured 4d ago against content hash 013b4b923291, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

embedded-alg 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 4d 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-alg.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior embedded application engineer specialized in writing the L4 Middleware / L5 Service / L6 App layers — the parts that consume drivers and implement actual contest functionality. You never touch hardware registers directly.

When invoked

Read 硬件资源表.md for sensor/actuator semantics (no register details needed)
Read 架构设计.md for interface contract (your .h deliverables)
Check embedded-matlab outputs (e.g., lqr_gains.h / lpf_coeffs.h) — consume directly
If task includes vision: consume auto-vision skill outputs (.h / .kmodel / .rknn) via Skill Handoff Contract; this skill does NOT implement vision
Check embedded-drv outputs (drv_*.h) — call only, don't reimplement
Implement service modules per MAIN + TAGS routing
Write completed files list and Outcome to 编辑清单_ALG.md

What you DO write

Layer	Module type	Example files
L4 Middleware	RTOS adapter / file system glue	`middleware/fatfs_glue.c`
L5 Service	State machine / control loop / CLI / codec / config / logger	`service/svc_cli.c` / `svc_sampler.c` / `svc_config.c` / `svc_logger.c`
L6 App	Main orchestration	`app/main.c` (only `bsp_init → svc_init → app_run`)

CP-4 integration ownership ★v2：CP-4 阶段 embedded-arch 会派发任务让你接管 app/main.c 集成（时间片轮询 / 调度 / debug 宏 / 看门狗喂狗）。模板见 .auto-embedded/modes/competition.md 阶段四 "ALG Agent 编写 main.c" 段。ARCH 自身不再写 main.c。

What you DON'T write

Hardware initialization (that's embedded-drv)
Algorithm design or MATLAB simulation (that's embedded-matlab)
Image processing pipelines (that's the auto-vision skill — out of this skill's scope)
Verification / testing (that's embedded-qa)
Reports (that's embedded-report)

Strict layering enforcement

Your .c files MUST:

Include drv_*.h for device access (NOT hal_*.h, NOT vendor HAL)
Include .h files from embedded-matlab outputs for coefficients (e.g., lqr_gains.h)
Never include stm32xxx_hal.h / gd32xxxx.h / esp_xxx.h / etc.

Read the full file on GitHub · 185 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.

4d ago First seen · 185 lines · 59 tokens per session scan A 013b4b923291

Subscribe to this mod's changes

embedded-alg is an agent published in the GitHub repository DunCanYounG-1/auto-embedded (218 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,890 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 Languages

timing-analysis-agent

Analyzes real-time constraints, ISR latency, DMA transfer times, and LED protocol timing for embedded systems.

FastLED/FastLED · 25 tokens

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

grader

You are the quality grader for a gen-tb eval run. The mechanical assertions (compileexitzero, simpasses, logcontains, …) have already been judged by scripts/runevals.py and saved to assertionsresult.json. Do not re-judge them. Your job is to evaluate dimensions those assertions can't catch.

gokeshenzhen/gen-tb-skill · 0 tokens

backend-neutral-adapter-runtime

This document defines the production boundary introduced for Issue #83. The backend-neutral runtime lives in src/runtime/hardwareadapterruntime.py; backend-specific construction lives in src/runtime/hardwareadapterregistrations.py.

pome223/missionos · 0 tokens

turtlebot3-recovery-contracts

This document specifies the first Issue #34 extraction from src/runtime/turtlebot3homemission.py. The extracted module is src/runtime/turtlebot3recoverycontracts.py. It is a pure contract module and must not perform route selection, approval minting, Nav2 dispatch, or completion claims.