codex-harness: Skill for Claude Code

.codex/skills/x-promo/SKILL.md

x-promo is a skill for Claude Code, Codex from Chachamaru127/codex-harness. It costs 56 tokens per session (1,929 once invoked), scanned A, original, MIT.

A Japanese-language guide for writing promotional posts on X, formerly called Twitter, for the Claude harness development project. It covers post structure, audiences, images or videos, and basic performance checks.

In plain words
What is it for?
Drafting posts, quote reposts, replies, audience-specific messages, and reusable templates about AI development, testing, quality assurance, and natural-language app building.
Why use it?
It turns project material into posts aimed at existing followers or wider reach while keeping the topic aligned with the account’s profile.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also installed under .codex/. Also seen: mentions Claude Code.

This is Chachamaru127/codex-harness's own configuration. It tells Claude Code and Codex how to work on codex-harness 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 codex-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Chachamaru127/codex-harness. 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/Chachamaru127/codex-harness/main/.codex/skills/x-promo/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Chachamaru127/codex-harness

Made for: Claude Code, Codex.

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 x-promo

README.md
[![agentmods](https://agentmods.dev/badge/skills/chachamaru127/codex-harness/x-promo.svg)](https://agentmods.dev/skills/chachamaru127/codex-harness/x-promo)
Your own site
<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/x-promo"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/x-promo.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,929 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00056 $0.01929
Opus 5 $0.00028 $0.00964
Sonnet 5 $0.00011 $0.00386
Haiku 4.5 $0.00006 $0.00193

Measured 8d ago against content hash 9eda7e467ac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

x-promo 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.

.codex/skills/x-promo/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

X投稿作成スキル(ハーネス専用・非配布)

注意: このスキルは claude-code-harness 開発専用です。.gitignore で除外されており、プラグイン配布には含まれません。

概要

Claude harness のプロモーション用X投稿を作成するスキルです。 Xアルゴリズム最適化のノウハウを活用して、効果的な投稿を生成します。


3つの基本原則

① プロフィールが超重要

知名度の高い単語を複数入れる。投稿にも同じ単語を含める。

プロフィールキーワード例:

  • Google, AI, ChatGPT, Claude Code
  • Vibecoder, ノーコード, AI開発
  • エンジニア, 個人開発

② Xアルゴリズムに「有益」と思わせる

判断ポイント:

  • 投稿の 独自性わかりやすさ
  • 既存フォロワーに 評価される内容

③ プロフィールキーワードを投稿に含める

プロフィールに書いていないカテゴリは扱わない。1アカウントで扱えるトピックは限られている。


投稿作成ガイドライン

バズと既存フォロワー向けの比率

タイプ 割合 目的
既存フォロワー向け 80% 固定ファンの維持
バズ狙い 20% 新規リーチ拡大

強い行動

1. 引用リポスト(超強行動)
構成:
1行目: 引用元に対して「明確な賛成 or 反対」を表明
2行目以降: 理由の補足、欠けている視点の追加

注意:
- 必ず画像または動画を添付(引用先の画像は消えやすい)
- 引用の引用の場合 → スクショを貼る
2. インプレゾンビ(リプ欄攻略)

狙い目:

  • 100万インプ以上
  • コメント欄が一言感想ばかり
  • 薄い内容のリプライが多い

戦略:

  • エビデンスベースで論理的な指摘
  • リプ欄の一番上に表示されやすくなる

投稿の品質管理

ルール 理由
10分以内に1いいねなければ削除 Xの評価を落とさない
URLは普通に貼る フォロワーに不便を強いない
一次情報・参考情報を示す 信頼性向上

Claude harness 投稿テンプレート

ターゲット別アプローチ

ターゲット キーワード 訴求ポイント
エンジニア AI開発, テスト, 品質保証 3層防御、テスト改ざん防止
バイブコーダー ノーコード, 日本語, アプリ開発 日本語で話すだけ
興味ある人 Claude Code, 始め方, 5分 ハードルの低さ
再チャレンジ 改善, 簡単, もう一度 以前より良くなった

投稿構成パターン

パターン1: 問題提起 → 解決
[問題] AIが〇〇する問題、ありませんか?

[解決] Claude harness なら〇〇できます。

✅ ポイント1
✅ ポイント2
✅ ポイント3

🔗 github.com/Chachamaru127/claude-code-harness

#ClaudeCode #AI開発
パターン2: Before/After
Claude harness 導入前後の変化

❌ Before: 〇〇だった
✅ After: 〇〇になった

[具体的な効果を1-2文]

#ClaudeCode
パターン3: Tips形式
Claude Code Tips 💡

〇〇するには、△△がおすすめ。

理由:
1. 〇〇
2. △△

試してみて👇
[コマンド or 手順]

#ClaudeCode #Tips
パターン4: アップデート告知
🎉 Claude harness v〇.〇.〇 リリース

新機能:
📚 〇〇
🔧 △△

これで〇〇が楽になります。

詳しくは👇
github.com/Chachamaru127/claude-code-harness

#ClaudeCode #アップデート

ハッシュタグ戦略

メイン(必須)

タグ 用途
#ClaudeCode 必須。メインタグ
#AI開発 汎用的

Read the full file on GitHub · 246 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 246 lines · 56 tokens per session scan A 9eda7e467ac8

Subscribe to this mod's changes

x-promo is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 1,929 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens