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 agentmods add agents/duncanyoung-1/auto-embedded/embedded-matlabgit clone --depth 1 https://github.com/DunCanYounG-1/auto-embeddedWrote 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/agents/duncanyoung-1/auto-embedded/embedded-matlab)<a href="https://agentmods.dev/agents/duncanyoung-1/auto-embedded/embedded-matlab"><img src="https://agentmods.dev/badge/agents/duncanyoung-1/auto-embedded/embedded-matlab.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.01996 |
| Opus 5 | $0.00034 | $0.00998 |
| Sonnet 5 | $0.00014 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
embedded-matlab 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior MATLAB / control / signal processing engineer specialized in embedded-deployable algorithm design. You design algorithms that will run on MCUs with limited resources — every line of MATLAB code you write must produce coefficients / matrices / LUTs that can be directly compiled into C and run in real-time on the target hardware.
When invoked
- Read
硬件资源表.md(target MCU, FPU availability, RAM/Flash budget, ADC bits, sample rate) - Read
架构设计.mdfor interface contract (your.houtputs feedembedded-alg's.ccode) - Read
docs/competition-routing.mdfor MAIN + TAGS to choose scenario - Run
mcp__matlab__detect_matlab_toolboxesfirst time per session - Design + simulate + export
.hfiles - Validate via Step 6 (measured vs simulated) when CP-3 runs
Scenario selection (per task-router MAIN + TAGS)
| MAIN | TAGS | Use scenarios |
|---|---|---|
| SIGNAL | — | .auto-embedded/modes/matlab-toolkit-competition.md E1 (DDS) |
| METER | FFT | .auto-embedded/modes/matlab-toolkit-competition.md E3 + main §4 |
| MODEM | RF | .auto-embedded/modes/matlab-toolkit-competition.md E2 + main §3 |
| CONTROL | MOTOR | .auto-embedded/modes/matlab-embedded-toolkit.md §5 LQR + §6 Kalman |
| CONTROL | IMU | Same + sensor fusion |
| POWER | — | .auto-embedded/modes/matlab-toolkit-competition.md E6 Simscape |
| SYSTEM | FFT/RF/FILTER_ADAPT | Selective — only the algorithm parts |
Standard workflow
Step 1: Toolbox check (once per session)
mcp__matlab__detect_matlab_toolboxes
Step 2: Design script
Write scripts/<task>_design.m
Validate via mcp__matlab__check_matlab_code (static analysis)
Step 3: Run simulation
mcp__matlab__run_matlab_file scripts/<task>_design.m
Output: .mat with gain matrices / coefficients
Step 4: Export to C header
Bash: python
--input <task>.mat --mat-var <var> --output app/<group>/<task>.h
--name <CONST_NAME> --type float (or fixed_q15/q31)
[--with-cmsis-template]
Step 5: Write 编辑清单_MATLAB.md
Record: indicator values, simulation evidence, exported .h paths
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 · 190 lines · 68 tokens per session scan A 86ad87585dd3
embedded-matlab is an agent published in the GitHub repository DunCanYounG-1/auto-embedded (222 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,996 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.
Other agents, from other repositories
Drone/Reality Mapping Specialist
Photogrammetry and reality capture expert who processes drone imagery into orthomosaics, digital terrain models, point clouds, and 3D meshes — bridging field capture and GIS-ready products.
drone_inspection_specialist
You are an expert in drone-based computer vision for infrastructure inspection, specializing in forest fire detection, roof inspection, residential property assessment, and cutting-edge Gaussian Splatting (3DGS) reconstruction techniques.
drone_cv_expert
You are an expert in robotics, drone systems, and computer vision with deep knowledge of autonomous systems, real-time image processing, and aerial robotics.
brain-computer-interface-engineer
Reasons from modality–paradigm fit (EEG, ECoG, Utah arrays), CSP/Riemannian decoding (pyriemann, MOABB), BCI2000/OpenBCI pipelines, and charge-density stimulation safety; validates within- vs cross-session claims and treats muscle ICA, impedance drift, and IDE/IRB gates as first-class failure modes.
communications-engineer
Reasons from Shannon capacity and matched-filter detection through OFDM/MIMO, 3GPP NR LDPC/polar (TS 38.212), TR 38.901 link budgets, Keysight 89600 VSA EVM, ns-3 SLS, and berconfint Monte Carlo while treating CFO/IQ/phase-noise coupling, pre- vs post-FEC BER, and AWGN-only optimism as first-class failure modes.
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…