letter-shell-integration

letter-shell-integration is a skill for Claude Code, Codex from easyzoom/aix-skills. It costs 37 tokens per session (775 once invoked), scanned A, original, MIT.

A guide for adding letter-shell, an embedded command shell that lets developers send commands to firmware through transports such as UART or RTT. It covers input handling, command registration, tasks, and access control.

In plain words
What is it for?
Use it to build or debug UART, USB, RTT, TCP, or custom firmware consoles, including command discovery, history, completion, login, and protected operations.
Why use it?
A shell can stop receiving input, block the system, or expose commands that erase data or change production settings if its transport and runtime setup are wrong. The guide checks those risks first.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build or debug UART, USB, RTT, TCP, or custom firmware consoles, including command discovery, history, completion, login, and protected operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/easyzoom/aix-skills/letter-shell-integration
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.

Any agent
npx skills add easyzoom/aix-skills --skill letter-shell-integration
Clone the repo
git clone --depth 1 https://github.com/easyzoom/aix-skills

Made for: Claude Code, Codex.

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 letter-shell-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/easyzoom/aix-skills/letter-shell-integration/github.svg)](https://agentmods.dev/skills/easyzoom/aix-skills/letter-shell-integration)
Your own site
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/letter-shell-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/letter-shell-integration/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 letter-shell-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/letter-shell-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/letter-shell-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 775 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 $0.00037 $0.00775
Opus 5 $0.00018 $0.00387
Sonnet 5 $0.00007 $0.00155
Haiku 4.5 $0.00004 $0.00077

Measured 9d ago against content hash 08af96cd0a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

letter-shell-integration 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.

skills/letter-shell-integration/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

letter-shell Integration

Overview

Use this skill to integrate letter-shell as an embedded debug console safely. Prove the transport, shell task or polling loop, command registration, and authorization policy before exposing commands that modify flash, reset devices, or change production state.

When To Use

Use this skill when:

  • The user wants to add or debug letter-shell in MCU firmware.
  • Shell input/output is missing, commands are not found, history/completion behaves wrong, or shell blocks the system.
  • The task involves UART shell, RTT shell, RTOS shell task, command export macros, login/password, or runtime debug commands.

Do not use this skill when the serial port itself is not trustworthy. Use embedded-serial-log-debug first.

First Questions

Ask for:

  • Target MCU/RTOS/compiler and letter-shell version or source.
  • Transport backend: UART, USB CDC, RTT, TCP, or custom.
  • Runtime model: polling loop, interrupt-driven RX, DMA RX, or RTOS task.
  • Existing shell config, command registration method, and linker section behavior.
  • Whether shell is allowed in production builds.
  • Commands that may be destructive, such as erase, reset, format, calibration, network write, or firmware update.

Integration Checklist

  1. Prove transport first. Confirm raw RX/TX works before debugging shell parsing.

  2. Create one shell instance. Bind it to explicit read/write functions and initialize it once.

  3. Decide scheduling model. Use a polling loop for simple bare-metal demos or a dedicated task/event-driven model for RTOS projects.

  4. Register one harmless command. Start with version, help, or status before adding state-changing commands.

  5. Confirm linker retention. If commands are exported through sections/macros, ensure the linker script and optimization settings keep them.

  6. Add access control for risky commands. Commands that erase flash, format filesystems, reset devices, change boot config, or modify calibration require explicit user/product approval.

Read the full file on GitHub · 94 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. 9d ago First seen · 94 lines · 37 tokens per session scan A 08af96cd0a5b

Subscribe to this mod's changes

letter-shell-integration is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 775 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 2026-08-30.

Related

Other skills, from other repositories

container-home

Answer questions, assist with planning, and help with design decisions for Mick's off-grid shipping container lake home project. Trigger when the user mentions the container home, lake home, Stewart County, LBL, the expansion, solar system, septic permitting, or retirement property.

mickpletcher/AI-Skills · 57 tokens

digital-twin-sync

Synchronize construction digital twins with real-time data. Connect BIM models with IoT sensors, progress updates, and field data for live project visualization and monitoring.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 36 tokens

drone-site-survey

Process drone survey data for construction sites. Generate orthomosaics, DEMs, point clouds, calculate volumes, track progress, and integrate with BIM models for comparison.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 40 tokens

json-parser

Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports. Transform nested JSON to flat DataFrames.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 28 tokens

equipment-fleet-manager

Manage construction equipment fleet. Track utilization, maintenance, and assignments.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 18 tokens

energy-efficiency

Audit a manufacturing energy management system for monitoring quality, cost optimization, and compliance. Triggers: building or reviewing industrial energy platforms, building management systems, or sustainability reporting tools.

tinh2/skills-hub-registry · 39 tokens