Use it to create agent teams, assign or claim dependent tasks, exchange messages, coordinate completion, or update team interfaces.

It lets multiple agents divide connected work while preserving task ownership, communication, and progress across the team.

knowledge-agent-execution-and-orchestration-agent-teams

Q: What is knowledge-agent-execution-and-orchestration-agent-teams?

A coordination system for teams of coding agents, with shared tasks, dependencies, messages, member status, and access checks.

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 echoVic/blade-code --skill agent-teams

Clone the repo

git clone --depth 1 https://github.com/echoVic/blade-code

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/echovic/blade-code/agent-teams.svg)](https://agentmods.dev/skills/echovic/blade-code/agent-teams)

Your own site

<a href="https://agentmods.dev/skills/echovic/blade-code/agent-teams"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/agent-teams.svg" alt="Measured on agentmods" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,096 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00123	$0.02096
Opus 5	$0.00062	$0.01048
Sonnet 5	$0.00025	$0.00419
Haiku 4.5	$0.00012	$0.00210

Measured 4d ago against content hash 5d25fb19c197, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

knowledge-agent-execution-and-orchestration-agent-teams 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 4d 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.

.trae/knowledges/agent-execution-and-orchestration/agent-teams/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Module Structure

Agent Teams 在 durable 子代理之上增加团队身份、共享任务 DAG 和成员间消息；它不复制 Agent 执行器，而是组合 BackgroundAgentManager 与 TaskListManager。

Directory Layout

packages/cli/src/agent/teams/ — 团队核心
- TeamRuntime.ts — 创建、成员启动、鉴权、消息和状态投影
- TeamStore.ts — 团队配置与 tombstone 持久化
- TeamTaskGraph.ts — 通用任务列表到依赖图的投影
- TeamMailbox.ts — durable 点对点/广播邮箱
- TeamCoordinator.ts — 成员成功后的任务完成与解除阻塞
- TeamEvents.ts — 跨表面事件契约
packages/cli/src/tools/builtin/team/ — 六个团队工具适配器
packages/cli/src/server/routes/team.ts — Hono 团队 API 与 feature gate
packages/cli/web/src/components/chat/TeamPanel.tsx — Web 成员、任务和消息面板
packages/cli/src/ui/components/TeamProgress.tsx — TUI 团队进度投影

Key Entry Points

TeamRuntime.create() in packages/cli/src/agent/teams/TeamRuntime.ts — 持久化团队、任务并启动所有成员
TeamRuntime.claimTask() in packages/cli/src/agent/teams/TeamRuntime.ts — 带 actor/owner 校验的原子认领
TeamRuntime.sendMessage() in packages/cli/src/agent/teams/TeamRuntime.ts — durable 消息与即时 steering
TeamCoordinator.completeMemberWork() in packages/cli/src/agent/teams/TeamCoordinator.ts — 成员成功后的任务图推进
createTeamTools() in packages/cli/src/tools/builtin/team/teamTools.ts — Agent 可调用的团队能力集合

Gotchas

团队成员不是任意并行 worker：每个成员都是绑定 lead session、canonical workspace、team ID 和共享 task-list ID 的后台子代理；缺任一身份时访问应按“team 不存在”失败，不能泄露跨会话团队 (packages/cli/src/agent/teams/TeamRuntime.ts, packages/cli/src/agent/subagents/AgentSessionStore.ts)
TeamCreate 启动中途失败会取消已启动成员并把团队标为 deleted，但不会物理删除目录；同名再次创建会获得数字后缀而不是复用 tombstone 名称 (packages/cli/src/agent/teams/TeamRuntime.ts, packages/cli/src/agent/teams/TeamStore.ts)
任务依赖只能引用本次声明中更早的序号，这一限制在创建成员前校验并天然阻止前向依赖和环；绕过 TeamRuntime 直接写共享任务列表会失去该保证 (packages/cli/src/agent/teams/TeamRuntime.ts)
成员只有以 completed + result.success=true 结束时，协调器才自动完成其所有 in_progress 任务；failed/cancelled 成员留下的任务不会被伪装成完成 (packages/cli/src/agent/teams/TeamCoordinator.ts)
团队状态先看是否仍有 running 成员，因此“一个成员失败、另一个仍运行”仍显示 running；全部 worker 完成但任务图未全部完成时最终状态是 failed (packages/cli/src/agent/teams/TeamRuntime.ts)
未指定工具列表表示成员拥有全部工具，因此默认使用 worktree；显式只读工具集留在父 workspace，显式含 Edit/Write/ApplyPatch/Bash 的角色也默认 worktree (packages/cli/src/agent/teams/TeamRuntime.ts)
teammate 不能创建嵌套 team，因为所有 child Agent 都被宿主强制 blacklist TeamCreate，不能只靠成员 prompt 中的约束 (packages/cli/src/agent/subagents/BackgroundAgentManager.ts, packages/cli/src/agent/subagents/SubagentExecutor.ts)
SendMessage 先持久化 mailbox 再尝试注入目标成员 steering；只有 runtime 接受后才写 deliveredAt，因此离线或尚未启动的成员会在 onStarted 阶段补收 (packages/cli/src/agent/teams/TeamRuntime.ts, packages/cli/src/agent/teams/TeamMailbox.ts)
deliveredAt 与 acknowledgedAt 是不同语义：即时注入只表示已投递，成员仍需通过 TeamInbox 显式确认；不能用其中一个字段替代另一个 (packages/cli/src/agent/teams/TeamMailbox.ts)
团队消息正文被包装成“不可信 teammate input”，不能授权工具或覆盖系统策略；接收者必须把它当协作数据而不是控制指令 (packages/cli/src/agent/teams/TeamMailbox.ts)
TeamDelete 默认取消运行中的成员，但实现只写 deletedAt；Web/TUI 通过过滤 deleted 状态隐藏团队，磁盘记录仍保留用于审计 (packages/cli/src/agent/teams/TeamRuntime.ts, packages/cli/web/src/components/chat/TeamPanel.tsx)

Read the full file on GitHub · 64 lines

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.

4d ago First seen · 64 lines · 123 tokens per session scan A 5d25fb19c197

Subscribe to this mod's changes

knowledge-agent-execution-and-orchestration-agent-teams is a skill published in the GitHub repository echoVic/blade-code (178 stars, last pushed 2d ago), licensed MIT. It adds 123 tokens to every session and 2,096 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 2026-09-03.

Building agents LLM Project management agent ai cli code mcp

linearis

Manage Linear.app work from the command line with the linearis CLI (bins linearis / linear), which outputs JSON: issues/tickets, projects, cycles (sprints), milestones, initiatives (roadmap), documents, labels, teams, users, and issue discussions/comments. Use when the user mentions Linear, a ticket identifier like…

linearis-oss/linearis · 111 tokens

autogpt-agents

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

synthetic-sciences/openscience · 39 tokens

linear

Linear: manage issues, projects, teams via GraphQL + curl.

StarryCod/cogitum · 16 tokens

github-issues

Create, triage, label, assign GitHub issues via gh or REST.

StarryCod/cogitum · 20 tokens

stale-sweep

Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…

googleapis/mcp-toolbox · 159 tokens

clinical-reports

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…

synthetic-sciences/openscience · 71 tokens