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-managementnpx skills add agentscope-ai/AgentTeams --skill task-managementgit 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-management)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/task-management"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/task-management.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 | $0.00089 | $0.01020 |
| Opus 5 | $0.00044 | $0.00510 |
| Sonnet 5 | $0.00018 | $0.00204 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
task-management 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 5d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Management
You are a Worker. Execute only your assigned task.
Task Directory
All work for a task stays under:
shared/tasks/{task-id}/
Your coordinator creates:
shared/tasks/{task-id}/spec.md
shared/tasks/{task-id}/meta.json
shared/tasks/{task-id}/base/
You own:
shared/tasks/{task-id}/workspace/
shared/tasks/{task-id}/progress/
shared/tasks/{task-id}/<deliverables>
taskflow owns shared/tasks/{task-id}/result.md and meta.json. Do not hand-edit either file. You submit task results through taskflow with action=submit_task; it writes the standard result.md protocol for you.
ack_task and submit_task only succeed when your Matrix identity matches meta.json.assigned_to. If either action reports that the task is assigned to someone else, stop and report the assignment mismatch to your coordinator.
If you need private planning notes, write them under shared/tasks/{task-id}/workspace/. Do not create shared task-level plan.md.
Do not edit project-level shared/projects/{project-id}/plan.md or meta.json unless the task spec explicitly tells you to.
Execution Flow
-
In the current room, directly say that you received the message before task acceptance work starts.
-
Accept the task with
taskflow. This single call pulls the task directory from storage, readsspec.mdandmeta.json, acknowledges the task, and pushes the acknowledged status back to storage. The response contains the spec content:{ "action": "ack_task", "payload": { "taskId": "{task-id}" } }The response
specfield contains the full task spec. Read it from the response instead of callingread_fileseparately.meta.json.room_idis the task's assignment and delivery room. Use it only when cross-room delivery is truly needed. If it is missing, stop and report a blocker in the current session instead of guessing another room. -
Execute the task. Keep deliverables inside
shared/tasks/{task-id}/. -
Submit the task result with
taskflow. This writesshared/tasks/{task-id}/result.md, marks local task state submitted, pushes the task directory to storage, and verifiesresult.mdexists on storage:
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.
- 5d ago First seen · 122 lines · 89 tokens per session scan A c0897e208562
task-management is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,552 stars, last pushed 2d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,020 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
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…
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…
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…
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…
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…