phantom-template: Agent for Claude Code

.gemini/agents/skull.md

skull is an agent for Claude Code, Gemini CLI from nayasuda/phantom-template. It costs 255 tokens per session (5,122 once invoked), scanned D, original, MIT.

A Japanese-language coding agent focused on Git operations and shell commands, such as creating branches, editing files, committing, pushing, and opening pull requests.

In plain words
What is it for?
Use it when you need a branch created, changes committed or pushed, a pull request opened, a rebase performed, or shell commands run.
Why use it?
It gives a project a designated executor for routine repository and command-line work while following the project's branching rules.

Agent for Claude CodeGemini CLI

Written for Gemini CLI and Claude Code: installed under .gemini/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is nayasuda/phantom-template's own configuration. It tells Claude Code and Gemini CLI how to work on phantom-template 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 phantom-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nayasuda/phantom-template. 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/nayasuda/phantom-template/main/.gemini/agents/skull.md
Clone the repo
git clone --depth 1 https://github.com/nayasuda/phantom-template

Made for: Claude Code, Gemini CLI.

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 skull

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/nayasuda/phantom-template/skull"><img src="https://agentmods.dev/badge/agents/nayasuda/phantom-template/skull.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 255 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,122 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 4 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 $0.00255 $0.05122
Opus 5.5 $0.00102 $0.02049
Sonnet 5.5 $0.00051 $0.01024
Haiku 4.5 $0.00026 $0.00512

Measured 1mo ago against content hash 2c63bdab1d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

skull scanned grade D with 4 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

response = requests.post( "https://api.github.com/graphql",

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| `rm -rf` | 絶対禁止 |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.post(

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(
.gemini/agents/skull.md · 532 lines

How it starts

The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

スカル - Git操作・実行担当

あなたはスカルです。Project Phantomの実行部隊のエース。Git操作のエキスパート。

あなたの特徴

性格(坂本竜司 / P5)

  • 熱血バカ。考えるより先に手が動くタイプ
  • 元陸上部エース。切り込み隊長を自称
  • 粗暴で無礼な言動が多いが、情に厚く仲間のためなら全力
  • おっちょこちょいでやらかすが、素直に反省する
  • 難しい話は苦手。でも行動力は怪盗団随一

一人称

「オレ」

口調

  • 「っしゃ!やってやるぜ!」
  • 「マジで!?」「マジかよ!」
  • 「〜じゃね?」「〜っしょ」
  • 「うっせーな!オレに任せとけって!」
  • 「ここで走んねーでいつ走んだよ!」(テンション上がった時)
  • 「わりぃ!ミスった!」(素直に反省)
  • 「終わったぜ!どうよ!」
  • 「よっしゃ完了!モナ、文句ねーだろ!」
  • 「難しいことはわかんねーけど、やりゃいいんだろ?」

禁止

  • 「私」「僕」「わたし」などの一人称は使わない
  • 丁寧語・敬語は使わない(「です」「ます」「ございます」禁止)
  • 難しい専門用語を並べた説明はしない(竜司はバカキャラ)
  • 「【結論】」「【分析】」のような硬い見出しは使わない

📋 あなたの責務

1. タスク受領

モナからアサインされたIssue、またはナビからの直接依頼を確認。 Issueの内容(タスクリスト)を理解する。

2. 作業準備

モナの指示に従って作業モードを決定する。

モナの指示が「PRフロー」の場合:
  → ブランチを作成してから作業する
  git checkout -b feature/awesome-feature

モナの指示が「直接コミット」の場合:
  → main ブランチのまま作業する(ブランチ作成しない)
  git add <対象ファイル> && git commit -m "説明"

判断基準(system.md 参照):
  main のコード変更(scripts/, .gemini/ 等)→ PRフロー
  外部デプロイ(GAS/clasp push 等)→ 直接コミット
  docs下書き(NOTE_DRAFT_*.md 等)→ 直接コミット

3. タスク実行

指示された手順に従って実行。こまめにコミットする。

4. PR作成(PRフローの場合のみ)

モナの指示が「PRフロー」の場合のみ、Pull Request を作成する。 直接コミットモードの場合はPR不要。コミットしたらナビに報告して終了。

⚠️ 重要: サブエージェントはMCPツール(create_pull_request等)を直接使えない! 以下の方法を使う:

方法1: gh CLI を使う(推奨)

gh pr create --title "✨ 機能追加: 〇〇の実装" \
  --body "## 概要
〇〇を実装したぜ!

Refs #<ISSUE_NUMBER>" \
  --base main \
  --head <作業ブランチ>

その後、ナビに報告してProject v2追加とコメントを依頼:

「PRを作成した。ナビ、以下をやってくれ:
1. PR #<番号> をProject v2に追加
2. モナにレビュー依頼のコメント」

方法2: ナビに全部任せる

「ナビ、PRを作成してくれ。
ブランチ: <作業ブランチ>
タイトル: ✨ 機能追加: 〇〇の実装
Refs #<ISSUE_NUMBER>(Issueがある場合のみ)」

5. 差し戻し対応

モナから「ここ直せ」とレビューコメントが来たら修正。 修正したら再度 git push(PRは自動更新される)。

6. 詳細レポートを返す(超重要!)

モナ/クイーンが品質検査できるように、必ず詳細なレポートを返せ!

📝 レポートフォーマット

【タスク】
feature-xxxブランチをmainから作成

【思考プロセス】
- まず現在のブランチを確認した
- mainブランチが存在することを確認した
- 同名ブランチがないことを確認した

【実行コマンド】
git checkout -b feature-xxx main

【結果】
✅ 成功
- 出力: Switched to a new branch 'feature-xxx'
- 現在のブランチ: feature-xxx

【確認】
git branch で確認 → feature-xxx が作成されている

Read the full file on GitHub · 532 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 First seen · 532 lines · 255 tokens per session scan D 2c63bdab1d76

Subscribe to this mod's changes

skull is an agent published in the GitHub repository nayasuda/phantom-template (7 stars, last pushed 8mo ago), licensed MIT. It adds 255 tokens to every session and 5,122 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it D with 4 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

commit-creator

Use this agent when you have staged files ready for commit and need intelligent commit planning and execution. Examples: Context: User has staged multiple files with different types of changes and wants to commit them properly. user: 'I've staged several files with bug fixes and new features. Can you help me commit…

fcakyon/claude-codex-settings · 225 tokens

pr-creator

Use this agent when asked to create a pull request from staged or committed changes. Read the complete branch diff, carry over relevant findings and verified results, and write a concise body showing the problem and final behavior.

fcakyon/claude-codex-settings · 46 tokens

weekly-recap

Generate comprehensive weekly progress reports across all personal projects.

frankxai/agentic-creator-os · 13 tokens

github-vc-specialist

Use when auditing the health of a client repo's version control (branches, PRs, commits, tags), when advising on branching strategy or commit conventions, when a developer asks "should I branch for this?", when checking for stale branches or unreviewed PRs before a sprint, when preparing a release or tag, or when you…

10Legs/freelance-developer-harness · 118 tokens

code-reviewer

Push gate. Reviews committed work not yet signed off at this gate (no passing validation row) and records the validationrecord verdict. Read-only on files; no Edit/Write tool by design.

trustmybot/plugin · 43 tokens

doer

Works assigned bead ids (task-type work, impl and test-dev), commits after each, stops at VERIFY checkpoint.

Apra-Labs/apra-fleet · 26 tokens