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/lianues/lim-code/using-subagentsnpx skills add Lianues/Lim-Code --skill using-subagentsgit clone --depth 1 https://github.com/Lianues/Lim-CodeWhat 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 | $0.00075 | $0.02911 |
| Opus 5 | $0.00037 | $0.01456 |
| Sonnet 5 | $0.00015 | $0.00582 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade A, and why
using-subagents 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 2d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 Subagents
背景知识
SubAgent 是无状态的:每一次调用的 SubAgent 都是无状态且独立的。它不会继承主 Agent 的聊天记录、主 Agent 已读过的 Skill、其他 Agent 的输出、上一轮结论,也不会知道主 Agent 脑中的计划。
中央数据库 / 共享信息库是同一概念:使用多个 SubAgents、多轮复核、审批、阻断项收敛或任何需要共享状态的任务时,公共事实、决策、阻断项、修订结果、审批结论必须写进外部位置,不能只留在聊天里。例如 docs/pm/{对应session主题名}/。
Skill 资源遵循渐进披露:先读取 Skill 主体;当 Skill 主体或任务需要引用附属资料时,再按 read_skill 返回的 resources manifest,用 read_skill_resource 按需读取 textReadable=true 的相关资源。不要无条件读取所有 resources。
集群并行调用 SubAgents 的方法:并行应该在单轮输出中同时调用多次 SubAgents 工具,禁止分轮次调用,除非一个 SubAgent 的输入信息依赖另一个 SubAgent 的输出。
调用前门禁
调用任何 SubAgent 之前,主 Agent 必须先判断任务类型。
一次性简单任务
如果任务不依赖上一轮结论、不依赖其他 SubAgent 输出、不需要审批收敛,也不需要后续复核,可以直接在 prompt/context 中完整写入目标、背景、约束、范围、输出格式和成功标准。
必须使用中央数据库的任务
只要满足以下任一条件,必须先建立或引用中央数据库 / 共享信息库,不允许只靠 prompt 摘要:
- 用户要求使用多个 Agents、SubAgents、并行 Agent、对抗性审查、多角色审查或集群处理。
- 任务出现“第一轮”“第二轮”“上一轮”“复核”“审批”“阻断项”“修订后”“Approve/Blocker 收敛”等语义。
- 需要多个 SubAgents 共享事实或接力。
- 需要后续 SubAgent 继承前一轮结论。
- 需要记录采纳、拒绝、阻断项、验证结果或最终决策。
- 任务会跨多次工具调用、多个 Agent 或多次对话轮次。
中央数据库推荐放在 docs/pm/{task-name}/,至少包含:
README.md:索引和文件用途。MASTER_CONTEXT.md:长期背景、目标、术语、边界和硬约束。STATUS.md:当前阶段、已完成项、阻断项和下一步。DECISIONS.md:已采纳/拒绝的关键决策和理由。reports/:每个 SubAgent 的调研、审查、审批、复核报告。
Agents Approve 迭代模式
当用户明确说出 进入agents approve迭代模式、进入 agents approve 迭代模式 或等价表达时,主 Agent 必须进入多 Agent 审批迭代流程。该模式不是普通并行审查,而是一个以 APPROVE / BLOCKER / CONCERN / NEEDS_INFO 为结论类型的闭环。
进入该模式后,主 Agent 必须:
- 建立或引用中央数据库 / 共享信息库。
- 将目标、长期背景、被审对象、通过标准、阻断标准、当前阶段和报告写入位置写入共享信息库。
- 并行派发多个 SubAgent 进行独立审查;每个 SubAgent 的 prompt 都必须自包含,或明确要求读取共享信息库中的指定文件。
- 汇总每个 SubAgent 的结论、证据、阻断项、关注项和缺失信息。
- 对确认采纳的阻断项进行修订,并把采纳 / 拒绝理由、修订摘要和验证结果回写共享信息库。
- 再次派发定向复核 SubAgent,直到没有阻断项、用户停止,或主 Agent 判断必须由用户作出产品、架构、安全或取舍决策。
本模式必须强制执行“SubAgent 无状态”这一全局不变量。当然,无论是否进入该模式,SubAgent 都不会自动继承聊天记录、主 Agent 记忆、上一轮结论或其他 SubAgent 输出;本模式只是把这条全局规则用于审批迭代场景,并要求每一轮的阻断项、修订摘要、审批结论和证据路径都回写到中央数据库 / 共享信息库。
复核和审批强制字段
二轮或后续复核、审批、阻断项收敛的 prompt 必须包含或引用以下内容;缺一项时不得派发 SubAgent:
- 中央数据库 / 共享信息库路径。
- SubAgent 开始前必须读取的文件列表。
- 上一轮报告路径。
- 上一轮完整问题清单,每个问题都要有证据路径、行号或来源。
- 本轮修订摘要,并逐条对应上一轮问题。
- 被复核对象路径。
- 期望验证点。
- 通过标准和仍然阻断的判定标准。
- 输出格式和报告写入位置。
- 缺失检查规则:如果无法读取中央数据库、上一轮报告或修订摘要,必须输出
REJECT: 缺少复核上下文,不得猜测。
What ships with it
6 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.
- 2d ago First seen · 142 lines · 75 tokens per session scan A 021bd686ab39
using-subagents is a skill published in the GitHub repository Lianues/Lim-Code (149 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 2,911 once invoked, about $0.0004 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 skills, from other repositories
mailbox-bridge
Use this skill when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox", "let Claude Code read the mailbox", "external agent mailbox", "mailbox bridge", or "HTTP mailbox bridge". Starts a loopback HTTP…
shadow-agent
Use this skill when you need a background monitoring agent that watches the fleet, detects anomalies, and can intervene on command. Triggers: user says "shadow", "monitoring agent", "fleet watcher", "hoop command", "spike detection".
backseat-driver-internals
Backseat Driver extension internals — Ex framework contracts, app-db state architecture, MCP socket server lifecycle, enrichment system, Datascript output log, activation sequences, and namespace reference. Use when: modifying core extension code, debugging state issues, working with app-db or Ex framework…
e2e-testing
E2E test authoring for Backseat Driver. Use when: writing, modifying, or debugging e2e tests under e2e-test-ws/, adding new MCP test scenarios, investigating test failures, understanding test infrastructure, or working with files matching test.cljs in the e2e workspace.
author
Scaffold a conforming AI-layer artifact — a rule, skill, hook, agent, or output style — that already passes the format checks, then verify it. Use when adding any new .claude/ artifact, so it matches the existing shape instead of drifting.
close
The "wrap" verb of the loop — end the session by writing the journal entry, updating touched project READMEs, committing, and pushing. Auto-invoked as the tail of /spec and /implement (the producer verbs) on clean completion, so "wrap" is not a verb the user types; also runnable directly. Dispatches /implement-audit…