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 Wafleem/stm32cubemx_mcp --skill configure-stm32cubemxgit clone --depth 1 https://github.com/Wafleem/stm32cubemx_mcpWrote 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/wafleem/stm32cubemx_mcp/configure-stm32cubemx)<a href="https://agentmods.dev/skills/wafleem/stm32cubemx_mcp/configure-stm32cubemx"><img src="https://agentmods.dev/badge/skills/wafleem/stm32cubemx_mcp/configure-stm32cubemx/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/wafleem/stm32cubemx_mcp/configure-stm32cubemx"><img src="https://agentmods.dev/badge/skills/wafleem/stm32cubemx_mcp/configure-stm32cubemx.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 | $0.00091 | $0.00720 |
| Opus 5 | $0.00046 | $0.00360 |
| Sonnet 5 | $0.00018 | $0.00144 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
configure-stm32cubemx 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 12d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure STM32CubeMX
Use the MCP as the deterministic execution layer. Analyze datasheets, schematics, images, and user requirements in the host agent before you create a structured tool call.
Workflow
- Call
cubemx_environment. Confirm that CubeMX is available. Review the allowed roots. - Call
cubemx_create_iocfor a new board or MCU configuration. Use the exact CubeMX identifier. Use only a new output directory. - Call
cubemx_list_iocwhen an existing IOC path is not known. Callcubemx_inspect_iocbefore you plan a change to an existing IOC file. - Resolve the requested MCU functions and pins from the available technical evidence. Do not state that the MCP read a datasheet or schematic.
- Call
cubemx_plan_ioc_changes. Usepin_assignmentsandenabled_peripheralsfor structural changes. Useparameter_updatesonly for known IOC parameter keys. - Show the planned changes, diagnostics, and source hash. Get user approval
before you call
cubemx_apply_ioc_changes, unless the user already gave explicit approval for that exact plan. - Apply the same plan request with
expected_source_sha256from the approved plan. Keep CubeMX validation enabled. Do not setskip_cubemx_validationunless the user explicitly requests the bypass and accepts the risk. - Use
cubemx_generate_projectonly for a new output directory. Usecubemx_plan_regenerationfor an existing STM32CubeIDE project. - Check
succeededbefore you report a completed generation or regeneration preview. Report all warning and error diagnostics. - Treat
output_directoryas the complete generated container. Treatproject_pathas the Eclipse project root. Do not assume that these paths are equal.
Safety rules
- Preserve PA13 and PA14 Serial Wire Debug (SWD) signals unless the user explicitly approves their reassignment.
- Do not use
parameter_updatesfor pin signals, labels, or lock states. - Stop if the source hash changes after the preview.
- Treat IOC validation, project generation, and compilation as different results.
- Do not state that an existing project was regenerated. The current tool only previews existing-project regeneration.
- Do not use
plan_idwhen a regeneration result hassucceeded=false. - Do not state that a project compiled. The MCP does not have a build tool yet.
- Report CubeMX diagnostics. Do not replace an unresolved configuration with a guessed setting.
What ships with it
1 file 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.
- 12d ago First seen · 59 lines · 91 tokens per session scan A 5005d446e6f8
configure-stm32cubemx is a skill published in the GitHub repository Wafleem/stm32cubemx_mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 91 tokens to every session and 720 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.