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 commands/ccplugins/awesome-claude-code-plugins/agent-manager-skillgit clone --depth 1 https://github.com/ccplugins/awesome-claude-code-pluginsWhat 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 | $0.00034 | $0.00291 |
| Opus 5 | $0.00017 | $0.00146 |
| Sonnet 5 | $0.00007 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
agent-manager-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Usage
/agent-manager-skill <TASK>
Goal
Help the user run and coordinate multiple local agents in parallel using tmux.
Instructions
-
Ask the user where
agent-manager-skillis installed (or have them clone it):git clone https://github.com/fractalmind-ai/agent-manager-skill.git -
Run a quick environment check:
python3 agent-manager/scripts/main.py doctor -
List configured agents:
python3 agent-manager/scripts/main.py list -
Based on the user task ($ARGUMENTS), start/assign/monitor agents:
python3 agent-manager/scripts/main.py start EMP_0001 python3 agent-manager/scripts/main.py assign EMP_0001 <<'EOF' $ARGUMENTS EOF python3 agent-manager/scripts/main.py monitor EMP_0001 --follow
Output
- Summarize which agents were started and what they are doing.
- Provide the exact commands to reproduce.
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.
- yesterday First seen · 49 lines · 34 tokens per session scan A 906dfd82a394
agent-manager-skill is a command published in the GitHub repository ccplugins/awesome-claude-code-plugins (926 stars, last pushed 19d ago), licensed Apache-2.0. It adds 34 tokens to every session and 291 once invoked, about $0.0002 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 commands, from other repositories
e2e-test-command
This is a mock slash command file for E2E testing.
atl-fetch-confluence
Command "atl-fetch-confluence" from lc-semba-ryuichiro/semba-claude-plugins, covering confluence 情報取得コマンド, コマンド実行, オプション, 実行例 and ページ情報を取得（json）.
atl-fetch-jira
Command "atl-fetch-jira" from lc-semba-ryuichiro/semba-claude-plugins, covering jira 情報取得コマンド, コマンド実行, オプション, 実行例 and 課題情報を取得（json）.
webpify-list
WebPファイルの一覧と情報を表示.
webpify
画像ファイルを WebP 形式に変換.
diagram-drawio
Command "diagram-drawio" from lc-semba-ryuichiro/semba-claude-plugins, covering draw\.io図作成コマンド, 実行手順, スキル参照（必須） and 出力オプション.