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 skills add agentscope-ai/AgentTeams --skill task-progressgit 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-progress)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/task-progress"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/task-progress/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/task-progress"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/task-progress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 35 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00043 | $0.00599 |
| Opus 5.5 | $0.00017 | $0.00240 |
| Sonnet 5.5 | $0.00009 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
task-progress 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 1mo 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.
What it actually says
Task Progress
Gotchas
- Push progress log after every meaningful action — don't batch updates; session resets can lose unpushed work
- task-history.json is LRU top 10 — overflow goes to
~/.hermes/history-tasks/{task-id}.json - Resume flow reads progress/ latest-first — keep filenames as
YYYY-MM-DD.mdfor correct sort order
Progress Log
After every meaningful action (completing a sub-step, hitting a problem, making a decision), append to:
~/shared/tasks/{task-id}/progress/YYYY-MM-DD.md
Format (append, don't overwrite):
## HH:MM — {brief action title}
- What was done: ...
- Current state: ...
- Issues encountered: ...
- Next step: ...
Push the task directory after each update:
mc mirror ~/shared/tasks/{task-id}/ ${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/ --overwrite --exclude "spec.md" --exclude "base/"
Task History (LRU Top 10)
File: ~/.hermes/task-history.json
{
"updated_at": "2026-02-21T15:00:00Z",
"recent_tasks": [
{
"task_id": "task-20260221-100000",
"brief": "One-line description of the task",
"status": "in_progress",
"task_dir": "~/shared/tasks/task-20260221-100000",
"last_worked_on": "2026-02-21T15:00:00Z"
}
]
}
Rules:
- New task assigned: add to head of
recent_tasks - Exceeds 10 entries: move oldest to
~/.hermes/history-tasks/{task-id}.json - Status changes: update
statusfield inrecent_tasks
Resume Flow
When your coordinator or admin asks you to resume a task after session reset:
- Read
task-history.json; if not there, checkhistory-tasks/{task-id}.json - Get
task_dirfrom the entry - Task files are already in
~/shared/tasks/{task-id}/(auto-synced). If you need the very latest, runhermes-sync - Read
{task_dir}/spec.md,{task_dir}/plan.md, and recent{task_dir}/progress/files (latest first) - Continue work and append to today's
progress/YYYY-MM-DD.md
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.
- 1mo ago First seen · 71 lines · 43 tokens per session scan A 2bf3a5a4b956
task-progress is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,768 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 599 once invoked, about $0.0002 per session on Opus 5.5. 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
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
slack-construct-agents
Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline. Ships as instructions.md composed into the group's CLAUDE.md at spawn; there is no workflow to invoke.
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
review-offered-task
Turn prompt for an offered swarm task: read the offer, accept with task-action and start work-on-task, or reject with a reason.