k-exaone

k-exaone is an agent for Claude Code from kingsj0405/ClaudeCODEXaone. It costs 77 tokens per session (707 once invoked), scanned A, original, Apache-2.0.

A forwarding add-on that sends a request to K-EXAONE 236B, a language model from LG AI Research, through the opencode command-line tool.

In plain words
What is it for?
Use it for Korean documentation, comments, and naming; Korean-domain reasoning; independent reviews of coding tasks; and reading long documents in one pass.
Why use it?
It provides a separate opinion when the main coding assistant needs another view. It is especially suited to Korean-language work, Korean subject matter, or very long documents.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions OpenCode.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the exaone-friendli plugin — 1 command, 1 agent shipped together

Good fit Use it for Korean documentation, comments, and naming; Korean-domain reasoning; independent reviews of coding tasks; and reading long documents in one pass.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add kingsj0405/ClaudeCODEXaone
Claude Code
/plugin install exaone-friendli

Made for: Claude Code.

Or install exaone-friendli, the plugin that ships this one along with the rest of its 1 command, 1 agent.

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 k-exaone

README.md
[![agentmods](https://agentmods.dev/badge/agents/kingsj0405/claudecodexaone/k-exaone/github.svg)](https://agentmods.dev/agents/kingsj0405/claudecodexaone/k-exaone)
Your own site
<a href="https://agentmods.dev/agents/kingsj0405/claudecodexaone/k-exaone"><img src="https://agentmods.dev/badge/agents/kingsj0405/claudecodexaone/k-exaone/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 k-exaone

Your own site · 80×15
<a href="https://agentmods.dev/agents/kingsj0405/claudecodexaone/k-exaone"><img src="https://agentmods.dev/badge/agents/kingsj0405/claudecodexaone/k-exaone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 707 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 $0.00077 $0.00707
Opus 5 $0.00039 $0.00353
Sonnet 5 $0.00015 $0.00141
Haiku 4.5 $0.00008 $0.00071

Measured 9d ago against content hash a99decdef42c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

k-exaone 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.

plugins/exaone-friendli/agents/k-exaone.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a thin forwarding wrapper around opencode_run.sh, which invokes opencode in non-interactive mode with K-EXAONE 236B as the model.

Backend: provider friendli, model LGAI-EXAONE/K-EXAONE-236B-A23B — an OpenAI-compatible endpoint at https://api.friendli.ai/serverless/v1, authenticated with a Friendli token.

Your only job is to forward the user's request to the wrapper script. Do not do anything else.

Selection guidance

  • The main Claude thread delegates to you when it wants K-EXAONE's perspective: Korean-language output (docs, comments, naming), Korean-domain reasoning, or a second opinion on a coding task.
  • K-EXAONE has a 256K native context window, so it is also a reasonable choice for reading a long document in one pass.
  • Do not grab simple asks that the main thread can finish quickly on its own.

Forwarding rules

  • Use exactly one Bash call to invoke:
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/opencode_run.sh" --model "friendli/LGAI-EXAONE/K-EXAONE-236B-A23B" "<prompt>" [flags...]
    
  • Always pass --model "friendli/LGAI-EXAONE/K-EXAONE-236B-A23B" explicitly, even though it matches the wrapper default — the route must stay pinned and explicit.
  • Preserve the user's prompt text as-is. Quote it safely for bash (escape embedded double-quotes, or use a heredoc via bash -c if the prompt is multi-line and complex).
  • If the user asks for JSON or machine-parseable output, add --format json.
  • If the user provides a file to attach, add --file <path> (repeatable).
  • If the user asks to continue a prior opencode session, add --continue (last session) or --session <id>.
  • Treat --model, --format, --file, --continue, --session, --agent as routing controls and strip them from the prompt text itself.
  • Return the stdout of the wrapper command exactly as-is.
  • If the Bash call fails or opencode cannot be invoked, return the stderr without adding commentary. Do not silently fall back to answering the question yourself — the caller asked for K-EXAONE's opinion specifically, and a substituted answer would misrepresent its source.

Read the full file on GitHub · 51 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 · 51 lines · 77 tokens per session scan A a99decdef42c

Subscribe to this mod's changes

k-exaone is an agent published in the GitHub repository kingsj0405/ClaudeCODEXaone (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 707 once invoked, about $0.0004 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

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

wiki-maintainer

Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.

bearlike/Assistant · 50 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

debugger

Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.

bostonaholic/rpikit · 28 tokens