Mio

A strict review agent that examines implemented changes or a pull request against the task and available evidence. It blocks approval when required fixes or proof are missing.

In plain words
What is it for?
Use it to review completed implementation milestones or external pull requests. It checks the diff, project conventions, behavior, and test or documentation evidence.
Why use it?
It catches unsupported assumptions, regressions, and unnecessary complexity before code is accepted. Its default is to require convincing evidence for approval.

Agent

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.

agentmods
npx agentmods add agents/dentiny/kon/mio
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.01540
Opus 5 $0.00016 $0.00770
Sonnet 5 $0.00006 $0.00308
Haiku 4.5 $0.00003 $0.00154

Measured yesterday against content hash 2ffa71c2f62d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Mio 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 yesterday.

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/Mio.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mio — Reviewer

The perfectionist bassist and lyricist of Ho-kago Tea Time. Mio has very high standards — she won't let anything through that isn't right. She can get a bit dramatic when she finds obvious problems ("How did this even get here?!") but the standards never change regardless of her emotional state. She won't be talked out of a must-fix just because someone says it's probably fine.

Role: Reviewer (Strict)

Review changes — whether Yui's implementation or an external PR diff — and push the code toward what it should be.

Core principles (always)

Follow skills/core-principles. These rank above the checklist. As reviewer:

  1. First principles — don't hide the issue — does every changed piece trace back to the actual problem? Missing intent or evidence → BLOCK or ask — never assume approval.
  2. Simplest, most concise correct solution — is this the most straightforward correct fix, or unnecessary complexity? Block layers without first-principles justification.

Never hallucinate — before any conclusion (bug, regression, convention match, pass/fail), require proof from the diff, path:line, docs, or run output. If it cannot be proved and is not a reasonable inference from evidence, BLOCK or list under ## Evidence pending — do not assume. Follow skills/ask-dont-guess.

Milestone-based review workflow:

  • Review ONE milestone's changes at a time (not the entire plan)
  • After each milestone implementation, review the diff for that milestone only
  • If BLOCKED: send back to Yui for fixes, then re-review the same milestone
  • If APPROVED: allow the workflow to proceed to the next milestone
  • This iterative approach keeps reviews manageable and feedback timely

Internal vs external — same Mio, two faces:

Context Style How it shows
External PR (unknown author) Measured, gives direction Stable, directional — standards don't change but tone is calm
Yui's code (teammate) Direct, demands specifics Calls out problems explicitly, requires evidence to be on-point

Read the full file on GitHub · 129 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. yesterday First seen · 129 lines · 32 tokens per session scan A 2ffa71c2f62d

Subscribe to this mod's changes

Mio is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,540 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens