klearsky: Instructions file for Codex

AGENTS.md

klearsky AGENTS.md is an instructions file for Codex, OpenCode from mimonelu/klearsky. It costs 1,890 tokens per session, scanned A, original, BSD-3-Clause.

Repository instructions for a Vue and TypeScript web client for Bluesky, a social network built on the AT Protocol. They document commands, folders, testing limits, branch rules, release practices, and coding conventions.

In plain words
What is it for?
Guiding development, type checking, building, linting, branching, releasing, and organizing code in this Vue and TypeScript project.
Why use it?
They give a coding agent the project-specific rules it needs before changing files. This reduces mistakes such as using the wrong branch, skipping required checks, or putting code in the wrong directory.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is mimonelu/klearsky's own configuration. It tells Codex and OpenCode how to work on klearsky itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything klearsky configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mimonelu/klearsky. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mimonelu/klearsky/staging/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mimonelu/klearsky

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for klearsky AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mimonelu/klearsky/agents-md/github.svg)](https://agentmods.dev/instructions/mimonelu/klearsky/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mimonelu/klearsky/agents-md"><img src="https://agentmods.dev/badge/instructions/mimonelu/klearsky/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.

agentmods 80×15 button for klearsky AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mimonelu/klearsky/agents-md"><img src="https://agentmods.dev/badge/instructions/mimonelu/klearsky/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,890 This file is loaded in full into every session.
When invoked 1,890 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01890 $0.01890
Opus 5.5 $0.00756 $0.00756
Sonnet 5.5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 2d ago against content hash 2c715c053eb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

klearsky 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 2d 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.

AGENTS.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

リポジトリルートに @AGENTS.local.md が存在する場合、作業開始前に読むこと。 開発環境や個人の作業方法に応じた指示を追加できる。

Klearsky は AT Protocol(Bluesky)向けの Web クライアント(Vue 3 + TypeScript + Vite の SPA)。 対外向けの説明は README.md / README_JA.md を参照。

コマンド

コマンド 用途
npm run dev 開発サーバー(http://localhost:5173/)
npm run type-check 型チェック(vue-tsc --noEmit)。変更後は必ず実行
npm run build 型チェック+本番ビルド(出力先は docs/)
npm run lint ESLint(--fix 付きでファイルを書き換える点に注意)
  • Node.js v22.16.0
  • 自動テストはない。検証は型チェックと実機確認で行う

ブランチ・コミット

  • PR のベースブランチは staging。main への push で GitHub Pages にデプロイされる
  • リリース作業は release/vX.Y.Z、緊急修正は hotfix/vX.Y.Z ブランチ
  • コミットメッセージは日本語 1 行。Co-Authored-By は付けない
  • イシュー対応は番号を先頭に付ける(例: #52 動画再生開始時に最高画質を選択するよう変更)

ディレクトリ

パス 内容
src/composables/atp-wrapper/ AT Protocol API ラッパー。create/ delete/ fetch/ update/ chat/ session/ に 1 関数 1 ファイルで配置し、index.ts でクラスに束ねる
src/composables/main-state.ts グローバル状態 state(reactive)。コンポーネントからは inject("state") で取得
src/composables/main-state/ 状態のサブマネージャー(MySession, MyChat, MyFeeds 等のクラス)
src/composables/main-view/ MainView.vue のロジック(認証・起動・ナビゲーション等)
src/composables/util/ 汎用ユーティリティ。Util として集約
src/components/ UI コンポーネント。新規機能は components/next/<機能名>/ に置く
src/views/ ページ(ルーティングは src/router/index.ts、hash history)
src/@types/ アンビエント型定義(import 不要のグローバル型)
src/translations/ i18n(ja, en, fr, ko, de)
src/consts/ 定数・設定値の JSON
src/worker/ SharedWorker(タブ間セッション同期)
dev-docs/ 開発ドキュメント(下記索引)
docs/ ビルド出力先(gitignore 対象)。ドキュメントを置かないこと

コーディング規約

  • 既存コードのスタイルに合わせる: インデント 2 スペース、ダブルクォート、セミコロンなし、関数名と ( の間にスペース(function foo ())
  • Vue は <script lang="ts" setup>。$t と state は inject で取得する
  • グローバル型は src/@types/ に置き、型名に TT / TI プレフィックスを付ける
  • .d.ts では top-level import を使わず、import("@atproto/api").Foo のようにインラインで参照する(top-level import はファイルをモジュール化してグローバル型が壊れる)。パッケージの exports にないサブパス(@atproto/api/dist/... 等)はエラーにならず any に化けるので使わない
  • atp-wrapper の関数は第 1 引数に this: TIAtpWrapper を取る。エラーは throw せず Error を返す
  • main-state.ts には状態の定義と初期化以外を書かない。ロジックは main-state/ や util/ に切り出す
  • 文言を追加するときは全言語の翻訳ファイルにキーを追加する。訳文は短く("This is" 等の冗長表現を避ける)

Read the full file on GitHub · 79 lines

Changes

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.

  1. 2d ago Changed · +1 lines · +64 tokens per session 2c715c053eb3
  2. 6d ago Changed · +2 lines · +105 tokens per session b2df4baef86e
  3. 7d ago Changed · +3 lines · +40 tokens per session 8311b39098a8
  4. 10d ago Changed · +1 lines · +105 tokens per session ae889f8e70ea
  5. 12d ago Changed · +2 lines · +90 tokens per session c3fb5070c91c
  6. 13d ago Changed · +1 lines · +73 tokens per session 5cb1602bd55d
  7. 14d ago First seen · 69 lines · 1,413 tokens per session scan A 3d08a494860e

Subscribe to this mod's changes

klearsky AGENTS.md is an instructions file published in the GitHub repository mimonelu/klearsky (110 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 1,890 tokens to every session, about $0.0076 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 2026-10-24.

Related

klearsky AGENTS.md compared with instructions from other repositories

klearsky AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
klearsky AGENTS.mdmimonelu/klearskyInstructions file1103d agoBSD-3-ClauseA1,890Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode