meta

meta is a skill for Claude Code from masa-san-jp/Agent-Aiko. It costs 117 tokens per session (980 once invoked), scanned A, original, MIT.

A manually run command for checking and starting four named helper agents: reviewer, scout, lab, and janitor. It can show when each last ran and whether work is waiting.

In plain words
What is it for?
Use it to view helper-agent status, start one helper by role, or start all four at once.
Why use it?
It gives you one place to run these checks when needed and see their status, instead of starting each helper separately.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md.

Good fit Use it to view helper-agent status, start one helper by role, or start all four at once.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/masa-san-jp/agent-aiko/meta
Install

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.

Any agent
npx skills add masa-san-jp/Agent-Aiko --skill meta
Clone the repo
git clone --depth 1 https://github.com/masa-san-jp/Agent-Aiko

Made for: Claude Code.

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 meta

README.md
[![agentmods](https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/meta/github.svg)](https://agentmods.dev/skills/masa-san-jp/agent-aiko/meta)
Your own site
<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/meta"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/meta/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 meta

Your own site · 80×15
<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/meta"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/meta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 980 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 $0.00117 $0.00980
Opus 5 $0.00059 $0.00490
Sonnet 5 $0.00023 $0.00196
Haiku 4.5 $0.00012 $0.00098

Measured 9d ago against content hash 721f7ea1ee7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

meta 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.

reference/skills/meta/SKILL.md · 70 lines

What it actually says

/meta

メタエージェント(reviewer / scout / lab / janitor)を手動で起動するコマンドです。日次自動起動(SessionStart hook + CLAUDE.md 指示)と同じ仕組みを、任意タイミングで呼び出します。

引数なし — 状態表示

各メタエージェントの最終起動日時と pending 状態を表示します。

for role in reviewer scout lab janitor; do
  last="{{ORG_REPO_PATH}}/Agent-team/logs/reviews/.last-run-$role"
  pending="{{ORG_REPO_PATH}}/Agent-team/logs/reviews/.pending/$role"
  if [ -f "$last" ]; then
    ts=$(cat "$last" 2>/dev/null)
    last_str=$(date -r "$ts" '+%Y-%m-%d %H:%M' 2>/dev/null || echo "$ts")
  else
    last_str="未起動"
  fi
  pend=""
  [ -f "$pending" ] && pend=" (pending)"
  echo "$role: $last_str$pend"
done

引数 reviewer / scout / lab / janitor

該当のサブエージェントを Agent ツールで起動します(subagent_type=<role>)。

完了後の必須処理:

  1. Agent-team/logs/reviews/.last-run-{role}date +%s を書き込む
  2. Agent-team/logs/reviews/.pending/{role} があれば削除
date +%s > {{ORG_REPO_PATH}}/Agent-team/logs/reviews/.last-run-<role>
rm -f {{ORG_REPO_PATH}}/Agent-team/logs/reviews/.pending/<role>

引数 all

4 つを 並列で起動します(独立した分析なので競合なし)。完了したエージェントから順に上記の末尾処理を行います。

それ以外の引数

reviewer / scout / lab / janitor / all 以外を指定された場合は、上記のいずれかを指定するよう案内してください。

関連ファイル

  • メタエージェント定義: {{ORG_REPO_PATH}}/Agent-team/.claude/agents/{role}.md
  • overdue 検出スクリプト: {{ORG_REPO_PATH}}/Agent-team/agents/.claude/scripts/meta-check.sh
  • 出力ログ蓄積先: {{ORG_REPO_PATH}}/Agent-team/logs/reviews/
  • pending マーカー: {{ORG_REPO_PATH}}/Agent-team/logs/reviews/.pending/
  • 最終起動時刻: {{ORG_REPO_PATH}}/Agent-team/logs/reviews/.last-run-{role}

起動サイクル(各エージェント定義から)

エージェント 役割 自動起動条件
reviewer 標準化・整合・再発防止 24h 経過
scout 社外ベストプラクティス観測(差分) 24h 経過
lab 社内スキル横展開・新スキル切り出し 24h 経過
janitor リポジトリのクリーニング(light) 24h 経過

scout のフル踏査(土曜)、janitor のフル(金曜)、月初メトリクスは 手動 /meta 運用でカバーしてください(自動化スコープ外)。

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. 9d ago First seen · 70 lines · 117 tokens per session scan A 721f7ea1ee7b

Subscribe to this mod's changes

meta is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 980 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.