Borrowing it
Nothing to install: this file belongs to kayba-ai/Kyoko. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kayba-ai/Kyoko/main/CLAUDE.mdgit clone --depth 1 https://github.com/kayba-ai/KyokoWrote 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/instructions/kayba-ai/kyoko/claude-md)<a href="https://agentmods.dev/instructions/kayba-ai/kyoko/claude-md"><img src="https://agentmods.dev/badge/instructions/kayba-ai/kyoko/claude-md.svg" alt="Measured on agentmods" 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 | $0.01165 | $0.01165 |
| Opus 5 | $0.00583 | $0.00583 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
Kyoko CLAUDE.md 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 8d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file gives coding agents the repo-specific context needed to work on Kyoko without re-learning the project from scratch.
Product Shape
Kyoko is a local repair loop for AI agent workflows:
telemetry -> issue -> proposal -> check -> replay -> gated apply
It is a single-user, local-first tool. The shipped runtime is a Python CLI, loopback dashboard/API, SQLite database, blob store, bundled dashboard assets, MCP server, telemetry SDKs, source/replay scaffolds, and conservative autonomy gate.
Read these first when the task touches product behavior:
README.mdfor the public overview.docs/SCOPE.mdfor v0 boundaries and non-goals.docs/ARCHITECTURE.mdfor the runtime model and safety boundary.docs/DEVELOPMENT.mdfor tests, dashboard builds, and release smoke.docs/specs/anddocs/fixtures/for contract-level behavior.
Current Names
The current package, module, and CLI are still named kyoko. Do not rename the
package, command, import path, docs, or release metadata unless the user
explicitly asks for that change.
Commands
# Local editable install
python3 -m pip install -e .
# Validate specs, schemas, fixtures, and bundled asset mirrors
python3 scripts/validate_gate_artifacts.py
python3 -m kyoko validate-gates
# Full Python test suite
python3 -m unittest discover -s tests
# First-run/safe local smoke
python3 -m kyoko doctor --safe-smokes --json
# Package install smoke
python3 -m kyoko release-smoke --artifact both --install-deps --json
There is no separate lint/format config. Match surrounding style.
Frontend
The dashboard source lives in frontend/. Vite builds into kyoko/assets/web/
so the Python package can serve the dashboard after installation.
cd frontend
npm install
npm run build
For frontend development:
python3 -m kyoko serve --db /tmp/kyoko.db
cd frontend
npm run dev
The dev server proxies API requests to kyoko serve. Push updates use
Server-Sent Events, not WebSockets.
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.
- 8d ago First seen · 143 lines · 1,165 tokens per session scan A 235876720912
Kyoko CLAUDE.md is an instructions file published in the GitHub repository kayba-ai/Kyoko (97 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,165 tokens to every session, about $0.0058 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.