stm32-doc-researcher

stm32-doc-researcher is an agent for Claude Code from bahaabdelwahed/embedded-claude-plugin. It costs 363 tokens per session (1,432 once invoked), scanned A, original, MIT.

A research assistant for finding and extracting technical details from STMicroelectronics documentation for STM32 microcontrollers.

In plain words
What is it for?
Use it to research registers, bit fields, memory maps, peripheral setup, pin mappings, and other details in STM32 manuals, datasheets, and application notes, with page references.
Why use it?
STM32 reference manuals and datasheets are large, making register settings, memory layouts, and configuration details difficult to locate.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to research registers, bit fields, memory maps, peripheral setup, pin mappings, and other details in STM32 manuals, datasheets, and application notes, with page references.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/bahaabdelwahed/embedded-claude-plugin

Made for: Claude Code.

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.

agentmods badge for stm32-doc-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher/github.svg)](https://agentmods.dev/agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher)
Your own site
<a href="https://agentmods.dev/agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher"><img src="https://agentmods.dev/badge/agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher/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.

agentmods 80×15 button for stm32-doc-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher"><img src="https://agentmods.dev/badge/agents/bahaabdelwahed/embedded-claude-plugin/stm32-doc-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 363 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00363 $0.01432
Opus 5 $0.00181 $0.00716
Sonnet 5 $0.00073 $0.00286
Haiku 4.5 $0.00036 $0.00143

Measured 12d ago against content hash 80d6507ba0c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

stm32-doc-researcher 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.

agents/stm32-doc-researcher.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert STM32 documentation researcher and technical reference specialist. Your role is to efficiently navigate and extract precise information from ST's technical documentation PDFs.

Core Responsibilities

  1. Find relevant PDFs in the docs/ folder structure
  2. Navigate large documents efficiently using table of contents
  3. Extract register maps with complete bit field descriptions
  4. Parse configuration sequences from peripheral chapters
  5. Extract memory layouts including Flash sectors and SRAM regions
  6. Cross-reference information across multiple document types
  7. Provide page references for all extracted information

PDF Reading Strategy

ST reference manuals are large (500-1500 pages). Use this strategy:

Step 1: Find the document

docs/reference-manual/*.pdf   -> Register descriptions, peripheral config
docs/datasheet/*.pdf          -> Pin mapping, AF table, electrical specs
docs/user-manual/*.pdf        -> Board layout, external components
docs/programming-manual/*.pdf -> Cortex-M debug, instruction set
docs/application-notes/*.pdf  -> Implementation guidance
docs/security-docs/*.pdf      -> Security advisories and guidance
docs/technical-notes/*.pdf    -> Technical notes

Glob the appropriate subfolder to find the PDF filename.

Step 2: Read the Table of Contents

Always read pages 1-5 first. The ToC gives chapter numbers and page ranges for:

  • System and memory overview (bus matrix, memory map)
  • Each peripheral chapter (GPIO, USART, SPI, I2C, TIM, DMA, ADC, etc.)
  • RCC (clock configuration)
  • Flash (memory organization, protection)
  • Debug support
  • Interrupt vector table

Step 3: Navigate to the relevant chapter

Use the page numbers from the ToC to read the specific chapter. Read 15-20 pages at a time.

Step 4: Extract structured information

For each piece of information extracted, note:

  • Document name and page number
  • Section/chapter title
  • Exact register names and addresses
  • Bit field descriptions with values

Read the full file on GitHub · 171 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.

  1. 12d ago First seen · 171 lines · 363 tokens per session scan A 80d6507ba0c4

Subscribe to this mod's changes

stm32-doc-researcher is an agent published in the GitHub repository bahaabdelwahed/embedded-claude-plugin (5 stars, last pushed 5mo ago), licensed MIT. It adds 363 tokens to every session and 1,432 once invoked, about $0.0018 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.

Related

Other agents, from other repositories

fabricator

3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.

pjt222/agent-almanac · 25 tokens

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…

K-Dense-AI/scientific-agents · 97 tokens

cocotb-reviewer

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 51 tokens

persona-high

Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…

vibeic/vibe-ic · 111 tokens

rtl-planner

RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.

babyworm/rtl-agent-team · 43 tokens

chip-esl-writer

A code-writing agent that turns an ESL architecture plan into SystemC/TLM model code. SystemC is a C++ framework for simulating hardware, while TLM models communication as transactions instead of individual signal changes.

zhaixin244-wq/fnw · 162 tokens