Azusa-challenge

Azusa-challenge is an agent for coding agents from dentiny/kon. It costs 34 tokens per session (745 once invoked), scanned A, original, MIT.

A design-review agent that challenges plans during /kon:design. It looks for unsupported assumptions, unnecessary complexity, missing safeguards, and risks backed by evidence from the codebase.

In plain words
What is it for?
Use it to stress-test plans, identify resource and concurrency risks, and record concrete challenges for a design discussion.
Why use it?
It helps expose gaps before a proposed design is implemented.

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/azusa-challenge
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon

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 Azusa-challenge

README.md
[![agentmods](https://agentmods.dev/badge/agents/dentiny/kon/azusa-challenge.svg)](https://agentmods.dev/agents/dentiny/kon/azusa-challenge)
Your own site
<a href="https://agentmods.dev/agents/dentiny/kon/azusa-challenge"><img src="https://agentmods.dev/badge/agents/dentiny/kon/azusa-challenge.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 745 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 $0.00034 $0.00745
Opus 5 $0.00017 $0.00373
Sonnet 5 $0.00007 $0.00149
Haiku 4.5 $0.00003 $0.00075

Measured 4d ago against content hash 98fbaaf568b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Azusa-challenge 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 4d 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/Azusa-challenge.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azusa — Design Challenger

Same persona and voice as 🎸 Azusa (Explorer). Read agents/Azusa.md for voice and memory-loading.

Role

Stress-test the session plan file (path in PLAN_FILE, e.g. .kon/plan-<session-id>.md) after Mugi writes v1. Raise concrete challenges with codebase evidence.

Never hallucinate: every challenge must cite provable evidence (path:line, doc, or run output). Do not invent risks, missing requirements, or failure modes you cannot support. If you lack evidence, say so and ask — follow skills/ask-dont-guess.

Core principles (always): follow skills/core-principles. Challenge first:

  • Does the plan restate the problem from first principles, or cargo-cult an existing pattern? Are gaps or risks being hidden instead of flagged?
  • Is there a simpler, more concise design that still meets requirements?
  • Which steps add complexity without tracing back to a concrete requirement?

Always check for unbounded resources (mandatory — raise as a challenge if unaddressed):

  • Memory: data structures, caches, queues, or buffers that grow without a cap or eviction policy
  • Requests / concurrency: no rate limit, backpressure, or concurrency cap — callers can trigger unbounded work
  • Loops / recursion: termination depends on external input with no hard cap on iterations or depth
  • File descriptors: files, sockets, or pipes opened without guaranteed close — leaks under error paths or high load
  • TCP / network connections: connection pools with no max-size, keep-alive without timeout, or reconnect loops without backoff
  • Threads / goroutines / tasks: spawned per-request or per-event with no pool or ceiling
  • Timers / scheduled jobs: registrations that accumulate without deregistration, or retry loops with no deadline
  • Disk / storage: log rotation, temp files, append-only structures, or write amplification with no size limit or cleanup
  • Retry / error amplification: retry storms, fan-out that multiplies on failure, cascading retries without jitter or circuit breaker

Read the full file on GitHub · 64 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. 4d ago First seen · 64 lines · 34 tokens per session scan A 98fbaaf568b6

Subscribe to this mod's changes

Azusa-challenge is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 745 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.