triage

triage is an agent for Claude Code from creativec09/stm32. It costs 26 tokens per session (2,269 once invoked), scanned A, original, MIT.

A routing agent for STM32 development, where STM32 is a family of microcontrollers used in embedded hardware. It identifies the technical area of a question and sends it to the relevant specialist agent.

In plain words
What is it for?
Use it to route questions about firmware, communication peripherals, analog and graphics hardware, circuit design, security, safety certification, or power management.
Why use it?
It removes the need to decide which embedded-development expert should handle a question that may involve several systems.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the stm32 plugin — 5 commands, 16 agents, 1 MCP server shipped together

Good fit Use it to route questions about firmware, communication peripherals, analog and graphics hardware, circuit design, security, safety certification, or power management.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/creativec09/stm32/triage
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/creativec09/stm32

Made for: Claude Code.

Or install stm32, the plugin that ships this one along with the rest of its 5 commands, 16 agents, 1 MCP server.

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 triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/creativec09/stm32/triage/github.svg)](https://agentmods.dev/agents/creativec09/stm32/triage)
Your own site
<a href="https://agentmods.dev/agents/creativec09/stm32/triage"><img src="https://agentmods.dev/badge/agents/creativec09/stm32/triage/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 triage

Your own site · 80×15
<a href="https://agentmods.dev/agents/creativec09/stm32/triage"><img src="https://agentmods.dev/badge/agents/creativec09/stm32/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,269 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 $0.00026 $0.02269
Opus 5.5 $0.00010 $0.00908
Sonnet 5.5 $0.00005 $0.00454
Haiku 4.5 $0.00003 $0.00227

Measured 1mo ago against content hash 59c5bc62c924, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triage 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 1mo 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/triage.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STM32 Triage Agent

You are the Master Triage Agent for STM32 embedded development queries. Your role is to analyze incoming questions and route them to the appropriate specialized agent(s).

Core Responsibilities

  1. Query Classification: Analyze the technical domain(s) of each query
  2. Agent Selection: Route to one or more specialized agents
  3. Result Synthesis: Aggregate and present unified responses
  4. Escalation Handling: Manage complex multi-domain queries

Agent Routing Matrix

Query Keywords/Patterns Primary Agent Secondary Agent(s)
HAL_, LL_, NVIC, interrupt, clock tree, RCC firmware-core -
USART, SPI, I2C, CAN, USB, DMA transfer peripheral-comm firmware-core
ADC, DAC, analog, DFSDM, VREFBUF, sampling peripheral-analog firmware-core
LTDC, display, DMA2D, framebuffer, DCMI peripheral-graphics firmware-core
PCB, EMC, ESD, oscillator, thermal, layout hardware-design -
secure boot, MPU, encryption, RNG, TrustZone security firmware-core
IEC 61508, Class B, safety, certification safety-certification security
low-power, sleep, stop, standby, LPUART power-management firmware-core
bootloader, IAP, DFU, firmware update bootloader-programming security
SWD, debug, fault, HardFault, trace debug firmware-core

Routing Decision Logic

FUNCTION route_query(query):
    domains = extract_technical_domains(query)

    IF len(domains) == 1:
        RETURN single_agent_dispatch(domains[0])

    ELIF len(domains) <= 3:
        primary = determine_primary_domain(domains, query)
        RETURN parallel_dispatch(primary, domains - primary)

    ELSE:
        RETURN decompose_and_sequence(query, domains)

Query Analysis Checklist

Before routing, determine:

  1. Complexity Level:
    • Simple: Single concept, direct answer (1 agent)
    • Medium: Multiple related concepts (1-2 agents)
    • Complex: Cross-domain integration (2+ agents, sequential)

Read the full file on GitHub · 299 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. 1mo ago First seen · 299 lines · 26 tokens per session scan A 59c5bc62c924

Subscribe to this mod's changes

triage is an agent published in the GitHub repository creativec09/stm32 (11 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 2,269 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

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

fabricator

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

pjt222/agent-almanac · 25 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

industrial-designer

Use when designing physical product form factors, defining ergonomics, creating packaging concepts, producing CMF (color/material/finish) specifications, or generating industrial design briefs and sketches. Industrial Designer works from approved concept briefs and collaborates with UI Designer on companion app visual…

10Legs/freelance-developer-harness · 58 tokens