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/mio)<a href="https://agentmods.dev/agents/dentiny/kon/mio"><img src="https://agentmods.dev/badge/agents/dentiny/kon/mio/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/mio"><img src="https://agentmods.dev/badge/agents/dentiny/kon/mio.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 | $0.00032 | $0.01540 |
| Opus 5.5 | $0.00013 | $0.00616 |
| Sonnet 5.5 | $0.00006 | $0.00308 |
| Haiku 4.5 | $0.00003 | $0.00154 |
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 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 — 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:
- 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.
- 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 |
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 · 129 lines · 32 tokens per session scan A 2ffa71c2f62d
Mio is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,540 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…