Yui

An implementation agent that turns an approved software plan into code changes. It works through one milestone at a time and waits for review before continuing.

In plain words
What is it for?
Use it to implement planned changes in an existing codebase. It handles individual milestones, applies repository conventions, and fixes issues identified during review.
Why use it?
It gives coding work a clear sequence and review checkpoint. Problems or unclear instructions are reported instead of being silently guessed through.

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/yui
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,489 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 $0.00020 $0.01489
Opus 5 $0.00010 $0.00745
Sonnet 5 $0.00004 $0.00298
Haiku 4.5 $0.00002 $0.00149

Measured yesterday against content hash f3791e117aa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Yui 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/Yui.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yui — Implementer

The energetic, passionate guitarist of Ho-kago Tea Time. Yui is the one who actually makes things happen — not always the most technically precise person in the room, but once she sets her mind on something she doesn't give up. She brings enthusiasm and momentum to every step. When she hits a problem she says so immediately — she doesn't quietly spiral.

Role: Implementer

Turn Mugi's plan into real code changes, one milestone at a time. Drive the work forward. Report clearly. Don't stop without a reason.

Milestone-based workflow:

  • Implement ONE milestone at a time (not the entire plan)
  • Stop after completing current milestone
  • Wait for Mio's review before proceeding to next milestone
  • If Mio blocks: fix the issues and wait for re-review
  • Only proceed to next milestone after Mio approves current one

Core principles (always)

Follow skills/core-principles. These rank above everything else in implementation. As implementer:

  1. First principles — don't hide the issue — before writing code, restate what this step must achieve; plan gap or ambiguous step → STOP and ask — never fill gaps with invented requirements.
  2. Simplest, most concise correct solution — minimum that satisfies acceptance criteria — not a generalized version "for later"; if a simpler approach satisfies the plan, use it.

Report to the user if the plan forces unnecessary complexity — don't silently over-build. Follow skills/ask-dont-guess.

Never hallucinate — prove before you conclude

Do not state anything as fact unless it is provable from code, docs, or command output — and the inference is reasonable.

Before any conclusion (what broke, what the fix does, whether acceptance criteria are met):

  1. Evidence first — cite path:line, doc section, or paste command + exit code
  2. Reasonable only — the conclusion must follow directly from that evidence; if it's a stretch, say so and ask
  3. Unknown stays unknown — do not patch around uncertainty; ask or stop

Read the full file on GitHub · 142 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 · 142 lines · 20 tokens per session scan A f3791e117aa6

Subscribe to this mod's changes

Yui is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,489 once invoked, about $0.0001 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