single-file-wbs: Instructions file for Codex

AGENTS.md

single-file-wbs AGENTS.md is an instructions file for Codex, OpenCode from piguo45/single-file-wbs. It costs 50,881 tokens per session, scanned A, a copy of skills AGENTS.md, MIT.

Project instructions for a single-file web viewer that displays work-breakdown structures and Gantt charts, including a progress line. Its data is stored in one JSON file and the viewer has no external dependencies.

In plain words
What is it for?
Use them when maintaining or extending the single-file WBS and Gantt viewer.
Why use it?
They give the coding agent the project’s structure and maintenance rules when changing this small web application.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is piguo45/single-file-wbs's own configuration. It tells Codex and OpenCode how to work on single-file-wbs 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 single-file-wbs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to piguo45/single-file-wbs. 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/piguo45/single-file-wbs/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/piguo45/single-file-wbs

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 single-file-wbs AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/piguo45/single-file-wbs/agents-md/github.svg)](https://agentmods.dev/instructions/piguo45/single-file-wbs/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/piguo45/single-file-wbs/agents-md"><img src="https://agentmods.dev/badge/instructions/piguo45/single-file-wbs/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 single-file-wbs AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/piguo45/single-file-wbs/agents-md"><img src="https://agentmods.dev/badge/instructions/piguo45/single-file-wbs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50,881 This file is loaded in full into every session.
When invoked 50,881 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 100% copy Near-identical to another mod 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 $0.50881 $0.50881
Opus 5.5 $0.20352 $0.20352
Sonnet 5.5 $0.10176 $0.10176
Haiku 4.5 $0.05088 $0.05088

Measured 1mo ago against content hash e536b5ff3153, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

single-file-wbs 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 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.

Origin

This is a copy

100% identical to skills AGENTS.md — 1,558 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 1,557 lines

How it starts

The opening of the file, as written. The whole thing — 1,557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

計画・課題管理ツール(WBS Viewer) - AGENTS.md

AI エージェント共通の説明書(Claude Code 2.1.277+・Codex ほか AGENTS.md を読む AI が対象)。旧 CLAUDE.md は 2026-09-24 にこの名前へ統一した(内容は同じ・symlink は置かない)。

English: AGENTS.en.md(本ファイルが正。仕様を変更したら ja/en を同じコミットで更新すること)

テキスト(JSON)駆動の管理ツール。計画(WBS)と課題(Issue)を 1枚の HTML・1つの JSON で回す。 データは「案件(projects[])の中に 計画(tasks)と課題(issues)が並ぶ」1つの JSON。 つながりは課題側の links[] にだけ書き、画面が逆引きして両方向へ1クリックで飛ぶ。

ファイル 位置づけ
wbs_viewer.html 製品の入口。これを開く。「計画|課題」の2択スイッチで切り替える(単一HTML・依存ゼロ)
wbs.json データの single source of truth。計画も課題もここに入る(ファイル名は自由。慣用名が wbs.json)

このファイル1本で、計画(tasks)も課題(issues)も完結する。 工数の式・ガント・イナズマ線・進捗の査定・課題の起票とクローズまで、すべてここに書く(説明書を別ファイルに分けない=AI が1本読めば済む)。 計画だけの従来の wbs.json(issues が無いファイル)もそのまま開ける(→「後方互換の約束」)。

読む順の目安:共通(ビジョン・原則・環境・画面・編集・データ)→ 計画(計算ロジック・追加と更新)→ 課題(導出値・4つの動き・依頼例)→ 異常系と制限 → 開発運用。


製品ビジョン・設計指針

AI時代の管理者(PL/テックリード)が、AIを含む少数精鋭チームを率いるためのローカルな計画表+課題表。人間はGUIで、AIは素のJSONと AGENTS.md で、同じ1枚を編集する。

  • 対象ユーザー:巨大プロジェクトのエンタープライズPMではなく、AIを含む10人規模の少数精鋭を率いる管理者(PL/テックリード)。作者自身がこのペルソナ=ドッグフーディング。
  • ビジョン(賭けと自覚):AI台頭で少数精鋭がAIを使いこなすのが主流になり、全員がPL/TL化する。そのリード(人間 and PL/TLエージェント)が計画と課題を管理する道具。未来への賭けだが、外れても今日のリードに刺さる=ヘッジ済み。
  • 核の差別化=2つの第一級インターフェース:人間=GUI/AI=素のJSON+AI可読な AGENTS.md。両方が第一級。全機能が GUI経路 と AI/JSON経路 の両方で動く(カスタムキー保持・round-trip)。
  • AGENTS.md は"ドキュメント"でなく"AIのAPI仕様":AIがフォーマットに依存するため、スキーマはほぼ動かさないを厳守。変える時は読む側の後方互換を保ち、AGENTS.md/AGENTS.en.md を同時に更新する。
  • 1つの入口で完結させる:AI は別リポの説明書を読めない。計画も課題も本ファイル1本に書き、参照は文書内で完結させる。
  • 正本ルール=リポ単位で宣言・1リポ1正本:課題の置き場をリポジトリごとに1つだけ決めて宣言する。GitHub Issue と課題表を混ぜない(どちらが本当か分からなくなる)。宣言は各リポの AGENTS.md に書く(本リポの宣言は末尾の「このリポの正本」節)。
  • 作る:事実だけを持つデータ(状態は導出)/載せる規律を支える欄(二つの問い・完了条件)/止まっている理由が必ず添う「待ち」と「凍結」/AIネイティブ(進捗査定・依存推定)/担当別の負荷(人間 vs AI の内訳)/コスト(_ai トークン・_money)/誠実なview(見栄えでなく真実の状態)。
  • 作らない:エンタープライズなチケット管理/エンタープライズPM(ポートフォリオ・複雑権限)/ワークフロー・承認フロー/大規模リアルタイム協業/通知・外部送信/自動集計レポート。
  • 意味論の出典 → 課題管理とはなにか?
  • 計画側の背景の論考 → WBSという至高ツールで、このAI時代をサバイブする

Read the full file on GitHub · 1,557 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. 1mo ago Changed · +74 lines · +4,548 tokens per session e536b5ff3153
  2. 1mo ago Changed · +1,482 lines · +46,329 tokens per session 880a7dd561d5
  3. 1mo ago First seen · 1 lines · 4 tokens per session scan A 6ebdb617a810

Subscribe to this mod's changes

single-file-wbs AGENTS.md is an instructions file published in the GitHub repository piguo45/single-file-wbs (131 stars, last pushed 1mo ago), licensed MIT. It adds 50,881 tokens to every session, about $0.2035 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to skills AGENTS.md, differing in 1,558 lines, and is treated as a copy.

Related

single-file-wbs AGENTS.md compared with instructions from other repositories

single-file-wbs AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
single-file-wbs AGENTS.mdpiguo45/single-file-wbsInstructions file1311mo agoMITA50,881Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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