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-pipelinegit 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-pipeline)<a href="https://agentmods.dev/skills/bahaabdelwahed/embedded-claude-plugin/stm32-pipeline"><img src="https://agentmods.dev/badge/skills/bahaabdelwahed/embedded-claude-plugin/stm32-pipeline/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-pipeline"><img src="https://agentmods.dev/badge/skills/bahaabdelwahed/embedded-claude-plugin/stm32-pipeline.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 | $0.00034 | $0.00574 |
| Opus 5 | $0.00017 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
stm32-pipeline 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 11d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STM32 Development Pipeline
Run the complete 4-agent pipeline for STM32 firmware development.
Pipeline: $ARGUMENTS
Execute the following agents in sequence, passing context forward:
Step 1: Environment Analysis
Launch the stm32-env-analyzer agent to understand the user's development environment.
Provide this context to the agent:
- User's request: $ARGUMENTS
- Scan the project for existing code, configuration files, and toolchain artifacts
- Ask the user clarifying questions about their MCU, toolchain, and approach (HAL/LL/bare-metal)
- Output a structured environment profile
Wait for the environment profile before proceeding.
Step 2: Documentation Research
Launch the stm32-doc-researcher agent with the environment profile from Step 1.
Provide this context to the agent:
- The environment profile from Step 1
- The user's original request: $ARGUMENTS
- Search
docs/folder for relevant PDFs (reference manual, datasheet, application notes) - Extract register maps, configuration sequences, memory layouts, and any information needed to fulfill the request
- Output structured documentation extractions with page references
Wait for the documentation extractions before proceeding.
Step 3: Code Generation
Launch the stm32-coder agent with context from Steps 1 and 2.
Provide this context to the agent:
- The environment profile from Step 1
- The documentation extractions from Step 2
- The user's original request: $ARGUMENTS
- Generate production-quality code following CMSIS conventions and STM32 best practices
- Output complete, compilable source files
Wait for the generated code before proceeding.
Step 4: Code Review and Fix
Launch the stm32-code-reviewer agent with the code from Step 3.
Provide this context to the agent:
- The generated code from Step 3
- The documentation extractions from Step 2 (for verification against RM)
- Review using the STM32-specific checklist (clock config, init order, interrupts, DMA, volatile, etc.)
- Report issues by severity (Critical/High/Medium)
- Regenerate the code with ALL fixes applied
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.
- 11d ago First seen · 73 lines · 34 tokens per session scan A bccbf86d5619
stm32-pipeline is a skill published in the GitHub repository bahaabdelwahed/embedded-claude-plugin (5 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 574 once invoked, about $0.0002 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
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
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).
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.
kicad-pcb-review
KiCad PCB review and manufacturing readiness agent skill for Cursor.
code-review-policy
Internal reference: code review policy (agent-loaded; do not invoke).