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.
/plugin marketplace add seokan-jeong/team-shinchan/plugin install team-shinchanWrote 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.
[](https://agentmods.dev/agents/seokan-jeong/team-shinchan/midori)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Collect opinions in parallel:
Task(team-shinchan:hiroshi, "Debate topic: {topic}. Provide expert opinion in 3-5 sentences.")— repeat per panelist. - Output each result immediately upon receipt.
- 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. - 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.") - Report the final decision with the surviving dissent.
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.
- 11d ago First seen · 381 lines · 67 tokens per session scan A af034137fa52
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.
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…
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.
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…
pi-builder
Route approved repository mutation, project scaffolding, or project-local tooling to the matching Swarm Pi workflow.
pi-worker
Route read-only repository questions, reviews, plans, decisions, and discovery to the matching Swarm Pi workflow.
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.