Koma

Miko: required Skill checks for Claude Code and Codex

Keep reminding your coding agent to read a required Skill before editing? Miko checks for observable Skill reads before protected edits. When evidence is missing, it pauses the action and tells the agent what to load before retrying. It runs locally, makes no LLM calls, and is free and open source.

The current focus is Claude Code and Codex CLI. Miko is part of Koma; the separate Gate, Scout, and Core packages cover AI application input, request limits, and retrieval. You do not need them to use Miko.

npm install -D koma-miko@alpha
npx koma-miko init --host claude

Edit the generated miko.json to name your project's Skills and protected paths, then start a new Claude Code session. Using Codex? Follow the Codex setup and one-time Hook review. Codex CLI is a Technical Preview; Desktop requires prior CLI activation.

中文版

▶ Try Miko's guided terminal replay — plus Gate, Scout & Core, no signup.

Miko for Claude Code and Codex

Coding agents can say they loaded a required Skill or ran a test. Miko does not treat that claim as evidence. At supported local host Hooks, it compares observed Skill loads, reference reads, tool actions, and completion checks with a project-owned miko.json.

If an agent tries to edit before satisfying the spec, Miko can return a denial and a short recovery instruction. It cannot inspect hidden model context, prove that a model understood a Skill, or verify events the host never exposes. In Claude CLI guided mode, a genuine scope exception opens one visible Miko choice: allow that exact retry once, or keep the current boundary.

npx --yes koma-miko@alpha demo       # deterministic; no API key
npx --yes koma-miko@alpha probe --host claude  # isolated adapter check; no model
npx koma-miko init --host claude     # after local installation

Codex CLI is a Technical Preview; Codex Desktop requires prior CLI activation. The CLI requires a one-time /hooks review before project Hooks run. Miko promotes enforce on Codex because the current Hook API cannot open a native REVIEW choice; review therefore degrades to a recoverable pause/deny. Desktop-only onboarding is not a supported alpha path. An offline probe proves adapter logic, not live Hook activation.

Miko README → · Current host support → · 10-second web replay →

Miko replay GIF · Still image — browser simulation, not a live host recording.

Claude Code is the primary alpha workflow. Codex CLI has a verified narrow recovery flow with the activation limits above. Gemini is outside active development; Copilot adapter work is paused pending a real tester. Existing adapters and their dated results remain available in the adapter documentation.

Why use Miko instead of writing a Hook? A small native Hook is enough for a single fixed check. Miko packages project Specs, observed-read tracking, post-compaction reload requirements, recovery messages, and completion evidence so you can maintain those checks together. Neither approach proves the model understood the instructions. See when Miko helps.

Four Boundaries

Different attacks cross different boundaries. Koma provides a small primitive for each one.

What Koma Is — and Isn't

Is: small composable packages · usable independently · explicit failure modes · deterministic checks where the host exposes evidence

Isn't: a model · an agent framework · proof that a model understood its instructions · a replacement for authorization · a complete security boundary by itself

Benchmarks

Miko alpha evaluation

Miko is deterministic, so its useful numbers are verifier cost and end-to-end Hook behavior—not a generic score for model intelligence.

The scale row is a 2026-08-27 reference run on Node 24.19 / Windows; rerun it with npm run eval:scale -w koma-miko. Context tokens never enter the verifier. The paid samples are deliberately small and do not establish general model, long-context, or editor reliability. See the scale record, Claude record, host-adapter record, and DSH record.

Koma Gate live-model benchmark

I threw 1,769 real prompt-injection attacks at Koma Gate in fail-closed mode, using real providers — not mock adapters.

Chinese attack set: 100% recall · 100% precision · 0% FPR across 8 categories.

Can you break it? Open an issue with an attack Koma misses. → Full methodology

Application-side quick start: Gate

import { createGeneralKnowledgeGuard } from 'koma-gate';

const guard = createGeneralKnowledgeGuard({
  llm: { apiKey: process.env.GEMINI_API_KEY },
});

app.post('/api/chat', guard.middleware(), async (req, res) => {
  // Only in-scope requests reach your model
  res.json({ reply: await chat(req.body.message) });
});

git clone https://github.com/swnotmetal/Project-Koma
cd Project-Koma && node demo/server.js
curl http://localhost:8080/self-test

Application-Side Packages

koma-gate — Prompt injection firewall. LLM-based scope classifier that blocks jailbreaks, off-topic requests, and instruction overrides. Supports OpenAI, Anthropic, Google, DeepSeek, and local Ollama models. README →

Try Gate in the browser demo →

koma-scout — Perimeter protection. Rate limiting, audio upload validation, geo allowlisting. Cheap checks before expensive AI work. README →