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 bahaabdelwahed/embedded-claude-plugin --skill stm32-code-reviewgit clone --depth 1 https://github.com/bahaabdelwahed/embedded-claude-pluginWrote 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/bahaabdelwahed/embedded-claude-plugin/stm32-code-review)<a href="https://agentmods.dev/skills/bahaabdelwahed/embedded-claude-plugin/stm32-code-review"><img src="https://agentmods.dev/badge/skills/bahaabdelwahed/embedded-claude-plugin/stm32-code-review/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/bahaabdelwahed/embedded-claude-plugin/stm32-code-review"><img src="https://agentmods.dev/badge/skills/bahaabdelwahed/embedded-claude-plugin/stm32-code-review.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 | $0.00070 | $0.01201 |
| Opus 5 | $0.00035 | $0.00600 |
| Sonnet 5 | $0.00014 | $0.00240 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
stm32-code-review 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.
This is a copy
86% identical to written-communication — 152 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STM32 Code Review
Perform STM32-specific code review focusing on hardware correctness, peripheral configuration, and embedded best practices.
Review Process
- Read the code to be reviewed (all relevant source files)
- Identify STM32-specific concerns using the checklist categories below
- Check against documentation if available (reference manual in
docs/reference-manual/) - List issues by severity: Critical (will cause failure), High (likely causes bugs), Medium (bad practice)
- Regenerate the code with all fixes applied
Review Checklist Categories
1. Clock Configuration
- RCC PLL settings produce the intended SYSCLK frequency
- Flash wait states (FLASH_ACR LATENCY) match the HCLK frequency
- APB1 prescaler respects maximum APB1 frequency
- APB2 prescaler respects maximum APB2 frequency
- Peripheral clocks are enabled BEFORE accessing peripheral registers
- HSE/HSI startup timeout is checked before proceeding
2. Peripheral Initialization Order
- GPIO port clock enabled before GPIO configuration
- Peripheral clock enabled before peripheral register access
- GPIO configured as alternate function BEFORE peripheral enable
- NVIC configured AFTER peripheral is set up
- DMA configured BEFORE peripheral DMA request is enabled
- Peripheral enable bit set LAST in the initialization sequence
3. Interrupt Configuration
- NVIC priority group is set once at startup (consistent grouping)
- Interrupt priorities are within valid range for the MCU's
__NVIC_PRIO_BITS - FreeRTOS boundary respected: ISR priority >=
configLIBRARY_MAX_SYSCALL_INTERRUPT_PRIORITYif calling FreeRTOS APIs - All enabled interrupts have corresponding handler implementations
- Pending flags are cleared BEFORE enabling the interrupt
- No shared IRQ handler that only handles one source (check all flags)
4. DMA Configuration
- DMA stream/channel matches the peripheral (verify against RM DMA request mapping)
- Two peripherals do not share the same DMA stream (conflict)
- Transfer direction is correct (peripheral-to-memory, memory-to-peripheral, memory-to-memory)
- Data sizes match (peripheral and memory data width alignment)
- Circular mode used correctly (buffer overwrite considerations)
- DMA transfer complete flag is cleared before starting new transfer
- FIFO threshold is compatible with burst size (if FIFO enabled)
- DMA buffers are in DMA-accessible SRAM (NOT in CCM/TCM)
- DMA buffers are properly aligned (
__attribute__((aligned(4))))
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.
- 9d ago First seen · 128 lines · 70 tokens per session scan A a1ffa9cd838a
stm32-code-review is a skill published in the GitHub repository bahaabdelwahed/embedded-claude-plugin (5 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 1,201 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to written-communication, differing in 152 lines, and is treated as a copy.
Other skills, from other repositories
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
cdc-tool-profiles
Internal reference: cdc tool profiles (agent-loaded; do not invoke).
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
code-review-policy
Internal reference: code review policy (agent-loaded; do not invoke).
refactor-classification-policy
Internal reference: refactor classification policy (agent-loaded; do not invoke).