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 coding-cligit 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/coding-cli)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/coding-cli"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/coding-cli/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/coding-cli"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/coding-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Privilege Escalation · line 88 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00047 | $0.01745 |
| Opus 5.5 | $0.00019 | $0.00698 |
| Sonnet 5.5 | $0.00009 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
coding-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding CLI Delegation
When the delegating agent (Manager / Leader / 获授权 Worker) assigns you a task with a "## Coding CLI Mode" section in spec.md, you do not write the code yourself. Instead, you:
- Understand the task deeply
- Prepare the workspace
- Generate a precise coding prompt
- Delegate execution to the delegating agent's CLI tool
- Review the result
Operational reference: references/delegation-guidance.md — one-shot delegation from the delegator's side: what it is, task-spec discipline, what it does not provide, and where results and logs land. Later capabilities (supervision, steering, approval) are documented in the management-side guidance.
When to Use This Skill
Check spec.md for the task. If it contains ## Coding CLI Mode, use this skill for all code changes.
Step-by-Step Workflow
1. Prepare the Workspace
Set up the workspace directory under the shared filesystem:
workspace="/root/agentteams-fs/shared/tasks/{task-id}/workspace"
mkdir -p "$workspace"
# Clone a repo (example)
git clone <repo-url> "$workspace"
# Or copy existing code
cp -r /path/to/source "$workspace/"
Constraint: The workspace path must be under /root/agentteams-fs/. The delegating agent accesses the same path via MinIO mirror.
2. Push Workspace to MinIO
Before sending the coding-request, push all workspace files so the delegating agent can access them:
mc mirror "/root/agentteams-fs/shared/tasks/{task-id}/workspace/" \
${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/workspace/
2b. Check for Processing Marker
Before modifying the workspace or sending a coding-request, check if the task directory is being processed:
# Sync latest state from MinIO
mc mirror "${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/" \
"/root/agentteams-fs/shared/tasks/{task-id}/"
# Check for processing marker
if [ -f "/root/agentteams-fs/shared/tasks/{task-id}/.processing" ]; then
echo "Task directory is being processed. Wait for the delegating agent to complete."
# Do NOT send coding-request yet; wait and retry
fi
What ships with it
1 file 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.
- 4d ago Changed · +4 lines · +17 tokens per session b812cef18158
- 1mo ago First seen · 180 lines · 30 tokens per session scan A 1ea8272a4bd8
coding-cli is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,768 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,745 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
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, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…
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…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…
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…