Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/u-ichi/reviewable-html-workbench/agents-mdgit clone --depth 1 https://github.com/u-ichi/reviewable-html-workbenchWrote 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/u-ichi/reviewable-html-workbench/agents-md)<a href="https://agentmods.dev/instructions/u-ichi/reviewable-html-workbench/agents-md"><img src="https://agentmods.dev/badge/instructions/u-ichi/reviewable-html-workbench/agents-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 | $0.01070 | $0.01070 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
reviewable-html-workbench 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reviewable-html-workbench
概要
HTMLを最終成果物にするagent workflow向けの共通plugin。図示つきHTML生成、Preview Runtime、HTML上のレビューコメント、コメント取り込み、agent返信、設計反映を扱う。
Claude Code / Codex CLI の両方で使えるように、plugin manifest は agent 別に持ち、skill本文とscript実装は共通化する。
技術スタック
- Python 3.11+
- 標準ライブラリ優先
- HTML / CSS / JavaScript
- Claude Code plugin (
.claude-plugin/plugin.json) - Codex plugin (
.codex-plugin/plugin.json) - Agent Skills (
skills/*/SKILL.md)
開発コマンド(自動テスト・構造検証)
以下は自動化された構造検証であり、機能の「動作確認」ではない。
# 自動テスト(コード正当性の検証)
python3 -m unittest discover -s tests
# Claude plugin manifest 検証
claude plugins validate .
# JSON syntax 検証
python3 -m json.tool .claude-plugin/plugin.json >/dev/null
python3 -m json.tool .codex-plugin/plugin.json >/dev/null
# CLI skeleton 確認
python3 -m scripts.html_review_workbench.cli --help
動作確認(実シナリオ検証)
このシステムの利用者は agent であり、Python CLI を直接叩く人間はいない。CLI は agent のツールである。「動作確認」とは CLI の入出力が正しい JSON を返すことではなく、agent がユーザーのワークフロー内で機能を正しく使えることを意味する。
自動テスト pass は動作確認の前提条件であり、動作確認そのものではない。
実シナリオ検証の手順は各 skill の SKILL.md「実シナリオ検証」セクションに記載。
ディレクトリ構成
.claude-plugin/Claude Code plugin manifest.codex-plugin/Codex plugin manifestskills/visual-html-renderer/HTML生成・図示・Preview Runtime用skillskills/reviewable-design-doc/レビュー可能な設計資料・コメント取り込み用skillscripts/html_review_workbench/両skillから呼ぶ共通実装templates/HTML/CSS/JSテンプレートtests/scriptとplugin構成の検証docs/設計・開発フロー
プロジェクト固有の規約
SKILL.mdは薄く保ち、重い処理はscripts/html_review_workbench/に置く。- Claude / Codex 差分は manifest と必要最小限のadapterに閉じ込める。
- コメントの確認質問はチャットだけで返さず、HTMLのコメントスレッドへ agent reply として書き戻す。
- Preview Runtime は Tailscale IPv4 を優先し、fallback は
127.0.0.1。0.0.0.0bindは禁止。 - 外部アップロード型の図式レンダラーは承認なしに使わない。
- git commit 時は必ず以下の 4 ファイル全て の
versionフィールドを同じ値に揃えて semver に従って更新する。バージョン更新なしの commit は禁止。.claude-plugin/plugin.json.codex-plugin/plugin.json.claude-plugin/marketplace.json(metadata.versionとplugins[0].versionの 2 箇所)pyproject.toml
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 · 79 lines · 1,070 tokens per session scan A 8fff4f9708cb
reviewable-html-workbench AGENTS.md is an instructions file published in the GitHub repository u-ichi/reviewable-html-workbench (295 stars, last pushed 26d ago), licensed MIT. It adds 1,070 tokens to every session, about $0.0053 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
research-papers-plugin CLAUDE.md
Claude Code instructions for ctoth/research-papers-plugin, covering research-papers-plugin, skill execution and release process.
apm python.instructions.md
Python development guidelines.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
CodexBar AGENTS.md
AGENTS.md instructions for bob-zebedy/CodexBar, covering repository guidelines, 项目结构与模块组织, 构建、测试与开发命令, 写作风格 and 代码和注释.
AGENTS.md AGENTS.md
AGENTS.md instructions for tkumata/AGENTS.md, covering global agent instructions, language, precedence, core rules and workflow and approval.