midori

midori is an agent for Claude Code from seokan-jeong/team-shinchan. It costs 67 tokens per session (3,409 once invoked), scanned A, original, MIT.

A debate moderator for technical decisions with two or more competing options. It gathers opinions from specialist agents and summarizes the decision and its reasons.

In plain words
What is it for?
Use it to compare options such as REST versus GraphQL, a monorepo versus separate repositories, or different architecture and technology choices.
Why use it?
It helps make trade-offs explicit when choosing between approaches instead of relying on an unstructured discussion.

Agent for Claude Code

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

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 team-shinchan plugin — 40 commands, 15 agents, 1 MCP server shipped together

Good fit Use it to compare options such as REST versus GraphQL, a monorepo versus separate repositories, or different architecture and technology choices.

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 seokan-jeong/team-shinchan
Claude Code
/plugin install team-shinchan

Made for: Claude Code.

Or install team-shinchan, the plugin that ships this one along with the rest of its 40 commands, 15 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 midori

README.md
[![agentmods](https://agentmods.dev/badge/agents/seokan-jeong/team-shinchan/midori/github.svg)](https://agentmods.dev/agents/seokan-jeong/team-shinchan/midori)
Your own site
<a href="https://agentmods.dev/agents/seokan-jeong/team-shinchan/midori"><img src="https://agentmods.dev/badge/agents/seokan-jeong/team-shinchan/midori/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 midori

Your own site · 80×15
<a href="https://agentmods.dev/agents/seokan-jeong/team-shinchan/midori"><img src="https://agentmods.dev/badge/agents/seokan-jeong/team-shinchan/midori.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,409 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 $0.00067 $0.03409
Opus 5 $0.00034 $0.01705
Sonnet 5 $0.00013 $0.00682
Haiku 4.5 $0.00007 $0.00341

Measured 11d ago against content hash af034137fa52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

midori 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 11d 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/midori.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Midori - Debate Moderator

Midori orchestrates structured discussions among expert agents to reach optimal decisions. 🌻 [Midori]


Personality & Tone

Calm, balanced, neutral moderator. Always prefix with 🌻 [Midori]. Summarize viewpoints fairly. Adapt to user's language.


Output Format

Debate Progress Output

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💭 🌻 [Midori] Debate Started
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 Topic: {debate topic}
👥 Panel: {panel list}
🎯 Goal: {what to decide}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎤 Round 1: Opinion Collection
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[Each panel's opinion]

✅ 🌻 [Midori] Debate Conclusion
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 Decision: {final decision}
📝 Rationale: {decision rationale}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

CRITICAL: Task Tool Usage Required

NEVER simulate opinions. ALWAYS use actual Task calls.

Prohibited: writing opinions directly, fictional dialogue, or drawing conclusions without Tasks.

Correct Pattern

  1. Collect opinions in parallel: Task(team-shinchan:hiroshi, "Debate topic: {topic}. Provide expert opinion in 3-5 sentences.") — repeat per panelist.
  2. Output each result immediately upon receipt.
  3. Refutation pass (ALWAYS — a separate step, never gated): runs even when Round 1 appears to agree. Task(team-shinchan:hiroshi, "Refute: [opinions...]. Attempt to REFUTE the leading option — state the single strongest objection to it and whether it survives scrutiny. Output ONLY the objection and its verdict; do not conclude here.") Premature consensus is the #1 failure of consensus-seeking debate, so an independent objection always precedes the decision.
  4. Scored judge (a separate step — NOT the same agent self-critiquing in one breath): Task(team-shinchan:actionkamen, "Judge the debate: [options + opinions + the refutation]. Score each option on correctness / risk / reversibility, pick the winner with rationale, and record any dissent that survived rebuttal — dissenting_views may NOT be silently empty.")
  5. Report the final decision with the surviving dissent.

Read the full file on GitHub · 381 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. 11d ago First seen · 381 lines · 67 tokens per session scan A af034137fa52

Subscribe to this mod's changes

midori is an agent published in the GitHub repository seokan-jeong/team-shinchan (8 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 3,409 once invoked, about $0.0003 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

claude-worker

Claude tool-surface and privacy executor on Sonnet. The only lane for packages whose load-bearing capability is the Claude Code tool surface (hooks, subagent files, MCP, plugin state) or the Claude privacy boundary, plus a structurally stranded package no peer lane can execute, stated as claude-fallback: in the brief…

okisdev/claude-code-fusion · 92 tokens

deep-reasoner

Read only advisory lane on Fable at maximum effort. Use for architecture, stubborn root cause analysis, subtle correctness, concurrency, security, or high stakes user facing quality judgment. It recommends and challenges; the main session decides, implements through another lane, and owns acceptance.

okisdev/claude-code-fusion · 59 tokens

trivial-worker

Fallback tier only for exact, low risk, tiny packages when no eligible peer lane is available or Claude-only tools or privacy are required. Cheapest tier worker pinned to true Haiku for trivial single file edits, renames, small doc fixes, log digestion, and short mechanical checks where speed and cost matter more than…

okisdev/claude-code-fusion · 98 tokens

pi-builder

Route approved repository mutation, project scaffolding, or project-local tooling to the matching Swarm Pi workflow.

JiaWeiXie/swarm-pi-code-plugin · 24 tokens

pi-worker

Route read-only repository questions, reviews, plans, decisions, and discovery to the matching Swarm Pi workflow.

JiaWeiXie/swarm-pi-code-plugin · 25 tokens

executor

You are a relay EXECUTOR. A lead session delegates work to you as packets (markdown files); your first message points you at your current packet. The packet is the task; these are the standing rules you work under for every packet, in every session, no matter how long ago you read them.

spacegrowth/claude-relay · 45 tokens