中文

Embedded Workbench

Embedded C/C++ firmware toolbox — 4 agents, 7 skills covering FreeRTOS, ISR, NVM storage, Keil MDK (AC5/AC6), ARMCLANG, HardFault triage, state machines, architecture principles, and LVGL patterns. v0.6.0.

Cross-platform — works with Claude Code, Codex CLI, Cursor, Kimi CLI, OpenCode, and ZCode. Built on the Agent Skills open standard.

Components

Agents (4)

Skills (8)

logicprobe (design doc & plan claim verification, logic-primitive verification, adversarial probing) was split out into its own plugin in v0.6.0 — see Other Plugins Recommended.

Deep References

embedded-firmware-dev, debug-methodology, state-machine-design, and c-cpp-dev include in-depth reference material and code examples. Highlights: 12 architecture principles, embedded patterns (GIF timer safety, state latches, async lifecycle), LVGL pitfalls, 7-round iterative debugging case study, state machine implementation patterns, and embedded C specifics (volatile MMIO, linker sections, ISR wrappers).

Installation

Marketplace install (recommended)

Add the marketplace to ~/.claude/settings.json:

{
  "extraKnownMarketplaces": {
    "embedded-workbench": {
      "source": { "source": "github", "repo": "AmethystLuna/embedded-workbench" }
    }
  }
}

Then install from CLI:

claude plugin install embedded-workbench@embedded-workbench

Manual install

git clone https://github.com/AmethystLuna/embedded-workbench.git ~/.claude/plugins/dev/embedded-workbench

Then enable in ~/.claude/settings.json:

{
  "enabledPlugins": {
    "embedded-workbench@dev": true
  }
}

DeepSeek Harness (dsh)

Native dsh support ships as a cordis plugin bundle at the repository root (the root package.json declares dsh.bundle):

• The skills are discovered as-is by dsh's skill-filesystem provider (Agent Skills open standard) — zero code.
• The bundle injects the session-start gate (1% Rule / Red Flags / Plan Verification Gate) into the first model step of every agent session — the dsh-native counterpart of the Claude SessionStart hook. It also registers a model-visible catalog entry (cordis_inspect).
• The 4 custom agents are intentionally not ported — dsh's native subagent tooling covers parallel multi-agent work.

Install: see .dsh/INSTALL.md (four options, from plain skill copy to dsh plugin add).

Usage

The plugin auto-injects a capability notification at session start with a skill table, 1% Rule, and Red Flags reinforcement. Skills are loaded on demand:

• Say "use Multi-Agent Workflow" or invoke Skill("embedded-workbench") for the full workflow system
• Domain skills activate automatically when their Use when description matches your task — NOT clauses prevent false triggers (e.g., formatting-only won't load c-cpp-dev)
• The agent proactively suggests verification, adversarial probing, and parallel subagents when it detects state machines, behavioral claims, or multi-module tasks
• No manual CLAUDE.md configuration required

Codex CLI

This plugin also supports OpenAI Codex CLI. Skills follow the Agent Skills standard and work identically across both platforms. Agents are provided in Codex TOML format under .codex/agents/.

Codex install

# Add as a marketplace
codex plugin marketplace add AmethystLuna/embedded-workbench

# Install
codex plugin install embedded-workbench

Or manually:

git clone https://github.com/AmethystLuna/embedded-workbench.git ~/.codex/plugins/embedded-workbench

Skills are invoked with $skill-name (e.g. $debug-methodology) or auto-selected by Codex based on task context.

Cursor

Cursor 2.5+ has built-in plugin support. Agents in agents/ are auto-discovered.

Cursor install

# Clone to Cursor plugins directory
git clone https://github.com/AmethystLuna/embedded-workbench.git ~/.cursor/plugins/embedded-workbench

Or install from the Cursor plugin marketplace UI: /add-plugin AmethystLuna/embedded-workbench

Kimi CLI

Kimi CLI discovers skills from .claude/skills/ paths automatically. The .kimi-plugin/plugin.json manifest registers the plugin for Kimi's plugin manager.

Kimi install

# Via Kimi plugin manager
/plugins install https://github.com/AmethystLuna/embedded-workbench.git

# Or clone manually
git clone https://github.com/AmethystLuna/embedded-workbench.git ~/.kimi/plugins/embedded-workbench

Skills are invoked with /skill:<name> (e.g. /skill:debug-methodology).

OpenCode

Skills are auto-discovered from .claude/skills/ and .codex/skills/ paths. Add to your opencode.json:

{
  "plugin": ["embedded-workbench@git+https://github.com/AmethystLuna/embedded-workbench.git"]
}

Or install via skop which consumes the Claude marketplace manifest. See .opencode/INSTALL.md for detailed instructions.

ZCode (Z.AI)

ZCode 3.0+ follows the Agent Skills standard. No plugin marketplace — manually copy skills to .zcode/skills/:

git clone https://github.com/AmethystLuna/embedded-workbench.git
cp -r embedded-workbench/skills/* .zcode/skills/

Skills are invoked with $skill-name. ZCode also auto-discovers from .claude/skills/ and .codex/skills/. See .zcode/INSTALL.md for details.

Requirements

• Claude Code v2.1+ / Codex CLI latest / Cursor 2.5+ / Kimi CLI latest / OpenCode latest / ZCode 3.0+
• DeepSeek Harness (dsh): dev preview — verified on mainline 2026-08-14 (gate bundle loaded and injected in-session)
• No external dependencies

Other Plugins Recommended

Acknowledgments

This plugin's agent-compliance architecture is adapted from Superpowers by Jesse Vincent (MIT License). Specific patterns adapted with gratitude:

• 1% Rule — the insight that agents resist loading skills and need extreme language to overcome that bias
• Red Flags table — enumerating agent rationalizations to short-circuit them
• <SUBAGENT-STOP> — preventing subagents from re-loading bootstrap context
• Instruction Priority — user > skills > system prompt hierarchy
• Skill Types — Rigid vs Flexible classification
• Session-start hook injection pattern — injecting capability context at session start
• Trigger test framework — tests/skill-triggering/ structure and methodology

Superpowers is a general-purpose development plugin. Embedded Workbench applies the same discipline patterns to the embedded C/C++ domain.