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 github-operationsgit 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/github-operations)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/github-operations"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/github-operations/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/github-operations"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/github-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02231 |
| Opus 5.5 | $0.00020 | $0.00892 |
| Sonnet 5.5 | $0.00010 | $0.00446 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
github-operations 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.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub PR & Issue Management
Overview
This skill allows you to manage Pull Requests and Issues via the centralized MCP Server. For git operations (clone, pull, push, commit, branch), use the git-delegation skill instead.
Environment Variables
No environment variables needed — mcporter reads its config from the default path ./config/mcporter.json automatically.
| Task | Use This Skill | Use git-delegation |
|---|---|---|
| Create/update/close PR | ✅ | |
| Review/merge PR | ✅ | |
| Comment on PR/Issue | ✅ | |
| Create/update/close Issue | ✅ | |
| Clone repository | ✅ | |
| Pull/fetch changes | ✅ | |
| Read/write files | ✅ | |
| Create branches | ✅ | |
| Commit/push code | ✅ |
How to Call GitHub Tools
Use mcporter CLI to call MCP Server tools:
# Method 1: key=value format (recommended for simple args)
mcporter \
call mcp-github.<TOOL_NAME> key1=value1 key2=value2
# Method 2: JSON format with --args flag (for complex objects)
mcporter \
call mcp-github.<TOOL_NAME> --args '{"key1":"value1","key2":"value2"}'
IMPORTANT:
- Always place
--configBEFORE thecallsubcommand - For JSON arguments, use the
--argsflag (not bare JSON string) - Use
mcp-github.<tool_name>selector format
Output
mcporter returns JSON output. Parse with jq for clean results.
Pull Request Operations
create_pull_request
Create a new Pull Request:
mcporter \
call mcp-github.create_pull_request --args '{
"owner": "higress-group",
"repo": "agentteams",
"title": "Add new feature",
"body": "## Summary\n- Change 1\n- Change 2\n\n## Test plan\n- [ ] Test A\n- [ ] Test B",
"head": "feature-branch",
"base": "main"
}'
list_pull_requests
List PRs in a repository:
mcporter \
call mcp-github.list_pull_requests owner=higress-group repo=agentteams state=open
get_pull_request
Get details of a specific PR:
mcporter \
call mcp-github.get_pull_request owner=higress-group repo=agentteams pull_number=1
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 · 405 lines · 50 tokens per session scan A ce81842a6bc9
github-operations is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,762 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 2,231 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.
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…
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…
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
gh-issues
Triage and execute GitHub issues with controlled agent workflows.
github
Operate GitHub workflows (issues, PRs, checks, releases) using approved tooling.