AgentTeams is a runtime platform where multiple AI agents collaborate in shared Matrix rooms under the coordination of a manager. It is for human-supervised or enterprise workflows that need visible, auditable cooperation among agents running on different runtimes, with shared files and centralized traffic management.
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/agentscope-ai/agentteams/task-delegationnpx skills add agentscope-ai/AgentTeams --skill task-delegationgit clone --depth 1 https://github.com/agentscope-ai/AgentTeamsWrote 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.
[](https://agentmods.dev/skills/agentscope-ai/agentteams/task-delegation)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/task-delegation"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/task-delegation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00056 | $0.01733 |
| Opus 5 | $0.00028 | $0.00866 |
| Sonnet 5 | $0.00011 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
teamharness-task-delegation 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 6d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Delegation
Use this skill when acting as Leader to create Project Work task specs, send assignment messages, and check submitted Worker results.
Each delegated task should have a task id, owner, scope, expected deliverables, acceptance criteria, and blocker reporting path. Write task instructions to the shared task directory before asking the owner to execute.
A submitted result is only a candidate result until accepted by the Leader. Do not use this skill to turn ordinary conversation into tasks.
Scope
Use this skill for:
taskflowcalls as Leader- converting a ready project node into a Worker task spec
- checking a submitted Worker result
- routing task assignment and completion messages
Use teamharness-project-management to create projects, plan DAG or Loop work,
resolve ready nodes, record Loop iteration decisions, and accept results into
project progress.
Delegate Only Ready Nodes
Use delegate_task only for Project Work nodes that are ready in project
state. Do not create bare tasks directly from a user request. First create or
update a project DAG, then delegate a ready project node returned by
projectflow readyNodes, or create/update a Loop and delegate a ready
project node returned by readyLoopNodes.
For Quick Task, projectflow create_quick_project is used instead. It
already writes shared/tasks/{task-id}/meta.json,
shared/tasks/{task-id}/spec.md, and marks the task assigned; do not call
delegate_task again for that task. create_quick_project does not
auto-notify, so after it returns ok: true, send the assignment message
described in the Assignment Message section below.
Before delegation:
- Resolve the Worker Matrix ID or stable member name from the team roster.
- Confirm the node came from
readyNodesorreadyLoopNodes. - Write a bounded task spec through
taskflow. The spec must include the completion report instruction below. - Keep Worker deliverables under
shared/tasks/{task-id}/.... Do not ask a Worker to write or submitshared/projects/...; project reports are Leader owned. - Use the current Matrix Task room for the assignment. Do not fall back to the requester/source session.
delegate_taskmentions the assigned Worker automatically after it succeeds — do not send a second mention.
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.
- 6d ago First seen · 197 lines · 56 tokens per session scan A f9fd750fb91b
teamharness-task-delegation is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,564 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,733 once invoked, about $0.0003 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
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively…