Borrowing it
Nothing to install: this file belongs to honishi/Hakumai. 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/honishi/Hakumai/main/AGENTS.mdgit clone --depth 1 https://github.com/honishi/HakumaiWrote 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/honishi/hakumai/agents-md)<a href="https://agentmods.dev/instructions/honishi/hakumai/agents-md"><img src="https://agentmods.dev/badge/instructions/honishi/hakumai/agents-md/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/instructions/honishi/hakumai/agents-md"><img src="https://agentmods.dev/badge/instructions/honishi/hakumai/agents-md.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 | $0.01602 | $0.01602 |
| Opus 5 | $0.00801 | $0.00801 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
Hakumai AGENTS.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 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hakumai Agents
This document defines the operational agents that are implemented in the Hakumai macOS app today. It is intended for contributors who add features, fix bugs, or design new automation around live comment ingestion and moderation support.
System Context
Hakumai is a desktop comment viewer for Niconico Live broadcasts. Agent responsibilities are split
across manager classes under Hakumai/Managers and orchestrated mainly by:
Hakumai/Controllers/MainWindowController/MainViewController.swiftHakumai/AppDelegate.swift
The current pipeline is:
- Authenticate and manage OAuth tokens.
- Resolve live metadata and stream endpoints.
- Ingest NDGR stream payloads (protobuf, chunked stream).
- Normalize payloads into
Chatand thenMessage. - Apply filtering, detection, and optional speech.
- Update UI, local notifications, and window indicators.
Communication Policy
- User-facing interactions must be localized for Japanese users.
- Internal logs, protocol payloads, and low-level diagnostics can remain English.
- This file is intentionally written in English for developer-facing clarity.
Agent Catalog
1. Session Agent
Primary components:
Hakumai/Managers/AuthManager/AuthManager.swiftHakumai/Managers/NicoManager/NicoManager.swiftHakumai/Managers/AuthManager/TokenStore.swift
Responsibilities:
- Validate token presence before live connection.
- Refresh access tokens when OAuth endpoints return invalid-token responses.
- Retrieve live info, user info, and websocket endpoint in order.
- Start and stop connection-related timers.
Failure behavior:
- If token refresh fails, stop connection setup and surface failure through delegate callbacks.
- On disconnect/reconnect conditions, hand off to reconnect flow with context and reason.
Security rules:
- Persist tokens only through keychain-backed storage (
SAMKeychain). - Never hardcode secrets or print raw credentials in logs.
2. Stream Ingestion Agent (NDGR)
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.
- 4d ago First seen · 212 lines · 1,602 tokens per session scan A b5011420d1c7
Hakumai AGENTS.md is an instructions file published in the GitHub repository honishi/Hakumai (35 stars, last pushed 2mo ago), licensed MIT. It adds 1,602 tokens to every session, about $0.0080 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 2026-09-04.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.