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 skills add masa-san-jp/Agent-Aiko --skill agent-callgit clone --depth 1 https://github.com/masa-san-jp/Agent-AikoWrote 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/skills/masa-san-jp/agent-aiko/agent-call)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/agent-call"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/agent-call/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.
<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/agent-call"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/agent-call.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00129 | $0.01228 |
| Opus 5 | $0.00064 | $0.00614 |
| Sonnet 5 | $0.00026 | $0.00246 |
| Haiku 4.5 | $0.00013 | $0.00123 |
Grade A, and why
agent-call 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agent-call
Agent-team 共通スキル。claude --print 経由で他エージェントへ 1 ターン委譲する。実装本体は {{ORG_REPO_PATH}}/Agent-team/tools/agent-call/。
サブコマンド
| 形 | 用途 |
|---|---|
/agent-call list |
利用可能なエージェント一覧を表示 |
/agent-call status |
claude CLI と agents/ の状態を表示 |
/agent-call <agent-name> "<prompt>" |
指定エージェントへ 1 ターン質問 |
実行手順
{{ORG_REPO_PATH}}/Agent-team/tools/agent-call/agent-call.sh <agent-name> "<prompt>"
stdin 経由で長文 prompt を渡すこともできる：
cat long_prompt.md | {{ORG_REPO_PATH}}/Agent-team/tools/agent-call/agent-call.sh <agent-name>
環境変数
| 変数 | 既定値 | 用途 |
|---|---|---|
AGENT_CALL_MODEL |
{{DEFAULT_MODEL}} |
呼び出し先の使用モデル |
WORKPLACE_ROOT |
{{ORG_REPO_PATH}} |
リポジトリルート |
AGENT_CALL_LOG |
1 |
0 でメタログ書き込みを無効化 |
AGENT_CALL_CACHE |
1 |
0 で agents 一覧キャッシュを使わず常に再スキャン |
メタログ
呼び出しごとに {{ORG_REPO_PATH}}/Agent-team/logs/agent-call/YYYY-MM-DD.jsonl へ 1 行追記する（AGENT_CALL_LOG=0 で無効化）。
| フィールド | 例 | 意味 |
|---|---|---|
ts |
2026-05-07T10:30:00+0900 |
呼び出し開始時刻（ISO8601） |
agent |
<agent-name> |
呼び出し先エージェント名 |
model |
{{DEFAULT_MODEL}} |
使用モデル |
duration_ms |
12340 |
実行時間（ミリ秒） |
exit_code |
0 |
claude プロセスの終了コード |
prompt_chars |
420 |
プロンプトの文字数（本文は記録しない） |
response_bytes |
1850 |
応答のバイト数（本文は記録しない） |
プロンプト・応答の 本文は記録しない（公開リポジトリでも安全な内容に限定）。
エージェント一覧キャッシュ
list / status / agent 名解決時に呼ばれる agents 一覧取得は、Agent-team/tools/agent-call/.cache/agents.json に JSON 配列形式でキャッシュされる。
| 比較対象 | 動作 |
|---|---|
| キャッシュ無し | スキャン → キャッシュ書き込み |
キャッシュ mtime ≥ agents/ ディレクトリ mtime |
キャッシュ参照 |
キャッシュ mtime < agents/ ディレクトリ mtime |
再スキャン → キャッシュ更新 |
agents/ 直下にエージェントが追加・削除されると同ディレクトリの mtime が更新されるため、次回呼び出し時に自動で再スキャンされる。.cache/ は .gitignore 対象（ローカル限定）。
AGENT_CALL_CACHE=0 で常にスキャンに戻せる。
実装ヒント
agent-call.sh は概ね以下の構造：
#!/bin/bash
# 1. agent-name を解決（cache or scan agents/ dir）
# 2. agents/<name>/ を cwd として claude --print --model $AGENT_CALL_MODEL
# 3. stdout を tee で取得しつつバイト数カウント
# 4. メタログに ts / agent / duration / exit_code / prompt_chars / response_bytes を append
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.
- 9d ago First seen · 88 lines · 129 tokens per session scan A 5cb038654c4a
agent-call is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 1,228 once invoked, about $0.0006 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.
Other skills, from other repositories
share-skills
Use when you need to author, package, or share a skill folder — understanding the SKILL.md format, where skills live, and how to bundle a folder so it can be shared with others.
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
A security record for agent skills, which are reusable instruction packages for coding agents. It shows their status, reviews risk exposure, and can certify them with quick or user-approved deeper scans.