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 skills/lirrensi/agent-sommelier/batch-task-executornpx skills add lirrensi/agent-sommelier --skill batch-task-executorgit clone --depth 1 https://github.com/lirrensi/agent-sommelierWhat 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 | $0.00106 | $0.01934 |
| Opus 5 | $0.00053 | $0.00967 |
| Sonnet 5 | $0.00021 | $0.00387 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
batch-task-executor 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 3d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Task Executor Skill
Coordinate many related work items from an arbitrary task source. The coordinator first figures out how to read the tasks and how to mark each task done, blocked, skipped, or failed in the same tracker/source. Only after intake and basic feasibility analysis does it decide whether to execute sequentially, fan out to workers, or ask for clarification.
This skill is experimental. Treat it as a planning and orchestration pattern first, not as a fixed CLI contract. Runtime-specific fan-out tools may differ across harnesses.
Project task systems: If the project you're working in already has a task tracker, ticket system, TODO list, or any form of work-tracking infrastructure — use that. Don't create a new tracking mechanism when one already exists. This skill integrates with whatever is already in place; the convention is to work within the existing project infrastructure rather than adding a parallel system.
Core Idea
The input does not define the workflow. A CSV, markdown checklist, Jira board, folder of files, pasted bullet list, test matrix, package list, or direct user prompt are all just ways to obtain a set of work items.
The stable contract is:
- Determine how to read the task source.
- Determine how to update the task source with status and optional comments, including how to mark work in progress.
- Normalize tasks into work items with stable ids and source references.
- Scout enough context to judge scope, risk, ordering, dependencies, and conflicts.
- Separate clear/easy work from blocked, ambiguous, dangerous, or mutually exclusive work.
- In interactive mode, ask only for clarifications that materially affect safety or correctness.
- In non-interactive mode, mark hard/blocked/unclear items and continue with safe items.
- Build an execution plan that separates sequential prerequisites from safe parallel groups.
- Execute through whatever tools/harnesses are available, bounded by safety and write policy.
- Verify reported completion before marking tracker items done.
- If work is incomplete, decide whether to retry, continue sequentially, mark blocked, or leave pending/stale.
- Update the tracker/source item-by-item or group-by-group with status and useful comments.
- Summarize final coverage, failures, blocked items, pending/stale items, and next actions.
What ships with it
5 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.
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.
- 3d ago First seen · 168 lines · 106 tokens per session scan A 6d448ec9aa11
batch-task-executor is a skill published in the GitHub repository lirrensi/agent-sommelier (5 stars, last pushed 28d ago), licensed MIT. It adds 106 tokens to every session and 1,934 once invoked, about $0.0005 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.