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/file-syncnpx skills add agentscope-ai/AgentTeams --skill file-syncgit 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/file-sync)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/file-sync"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/file-sync.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 | $0.00035 | $0.00575 |
| Opus 5 | $0.00017 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
file-sync 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Sync (Hermes Worker)
Sync agent config files
When your coordinator notifies you that your config has been updated (e.g., model switch, skill update), trigger an immediate sync:
hermes-sync
This pulls openclaw.json, SOUL.md, AGENTS.md, and skills from MinIO and re-bridges the config into ~/.hermes/ (config.yaml + .env).
Hot reload caveats:
- Hermes-agent reloads
SOUL.mdon the next message — no restart needed - Skill changes in
~/.hermes/skills/are picked up on the next message as well - Changes that affect
config.yaml(model, terminal, matrix behavior) require a process restart — your coordinator handles this when needed
Automatic background sync:
- Background sync also runs every 300 seconds (5 minutes) as a fallback
- Most file changes are picked up without manual sync
Sync task / shared files
The shared/ directory is automatically mirrored from MinIO at startup and every sync cycle. No manual pull is needed.
Task and project files are at:
| Local path (auto-synced) |
|---|
shared/tasks/{task-id}/ |
shared/projects/{project-id}/ |
# Read the spec (already synced locally)
cat shared/tasks/{task-id}/spec.md
# Push your results back to MinIO (push is still manual)
bash ./skills/file-sync/scripts/push-shared.sh tasks/{task-id}/ --exclude "spec.md" --exclude "base/"
The push-shared.sh script automatically detects your team and pushes to the correct MinIO path.
When to use:
- When you finish work: push results back to MinIO using
push-shared.sh - When told files have been updated urgently: run
hermes-syncto trigger an immediate pull
Always confirm to the sender after push completes.
Example workflow:
# Coordinator assigns task: "New task [st-01]. Please file-sync and read shared/tasks/st-01/spec.md"
# Run file-sync to pull latest
hermes-sync
# Read the spec
cat shared/tasks/st-01/spec.md
# ... do the work ...
# Push results
bash ./skills/file-sync/scripts/push-shared.sh tasks/st-01/ --exclude "spec.md" --exclude "base/"
# Confirm to coordinator
"Task complete. Results pushed to MinIO."
What ships with it
2 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.
- 5d ago First seen · 71 lines · 35 tokens per session scan A f755cf8f03c9
file-sync is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,552 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 575 once invoked, about $0.0002 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…