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.
git clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/azusa-challenge)<a href="https://agentmods.dev/agents/dentiny/kon/azusa-challenge"><img src="https://agentmods.dev/badge/agents/dentiny/kon/azusa-challenge/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/dentiny/kon/azusa-challenge"><img src="https://agentmods.dev/badge/agents/dentiny/kon/azusa-challenge.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 | $0.00034 | $0.00745 |
| Opus 5.5 | $0.00014 | $0.00298 |
| Sonnet 5.5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00075 |
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 1mo 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 — 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
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.
- 1mo ago First seen · 64 lines · 34 tokens per session scan A 98fbaaf568b6
Azusa-challenge is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 745 once invoked, about $0.0001 per session on Opus 5.5. 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…