teammates-config

teammates-config is a skill for Claude Code from andreymudri/claude-teammates. It costs 24 tokens per session (1,413 once invoked), scanned A, original, MIT.

Configuration instructions for a fleet of teammates, meaning multiple agents working on a task. They describe which settings control parallel work and each role’s model tier or effort.

In plain words
What is it for?
Adjusting agent parallelism, model tiers, effort levels, and checking the project’s tracked enforcement settings.
Why use it?
They prevent changes to enforcement settings through the wrong configuration file or command.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-teammates plugin — 14 skills, 3 agents, 2 hooks shipped together

Good fit Adjusting agent parallelism, model tiers, effort levels, and checking the project’s tracked enforcement settings.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add andreymudri/claude-teammates
Claude Code
/plugin install claude-teammates

Made for: Claude Code.

Or install claude-teammates, the plugin that ships this one along with the rest of its 14 skills, 3 agents, 2 hooks.

Wrote 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.

agentmods badge for teammates-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/andreymudri/claude-teammates/teammates-config/github.svg)](https://agentmods.dev/skills/andreymudri/claude-teammates/teammates-config)
Your own site
<a href="https://agentmods.dev/skills/andreymudri/claude-teammates/teammates-config"><img src="https://agentmods.dev/badge/skills/andreymudri/claude-teammates/teammates-config/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.

agentmods 80×15 button for teammates-config

Your own site · 80×15
<a href="https://agentmods.dev/skills/andreymudri/claude-teammates/teammates-config"><img src="https://agentmods.dev/badge/skills/andreymudri/claude-teammates/teammates-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01413
Opus 5 $0.00012 $0.00707
Sonnet 5 $0.00005 $0.00283
Haiku 4.5 $0.00002 $0.00141

Measured 11d ago against content hash d541e851e3d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

teammates-config 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 11d 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.

skills/teammates-config/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teammates Config

What config covers, and what it does not

config manages the ergonomics keys only: maxParallel, caveman, and agents.<role>.tier/agents.<role>.effort. Those are the only keys config set/config unset accept, in either layer, subject to the enforcement rule below.

teammates.gate.json is tracked and can also hold the enforcement keys phases, lens, and preview. Those are edited by hand, deliberately: enforcement policy is meant to land as a reviewable diff in a tracked file, not as a CLI mutation. config set lens ..., config set phases ..., and config set preview ... all fail with unknown config key: <key> and exit 2 — this skill never attempts them. Neither does config get: it routes through the same key allowlist as set, so config get lens (or phases/preview) also exits 2 with unknown config key: <key>. Never reach for config get to check a hand edit to one of these three keys — read the file, or use config list as described below, which is a real but partial check.

teammates.local.json is gitignored and holds only the ergonomics keys. An enforcement key never goes in the local file — the CLI rejects the attempt by name with exit 2, even if a caller reaches for it through agents.reviewer.*: the reviewer produces the verdict for agent-kind checks, so its tier and effort are enforcement, not ergonomics, and are rejected from the local layer for the same reason phases, lens, and preview are.

What caveman actually reaches

Measured 2026-08-25 against real subagent transcripts. caveman is a much narrower knob than its position beside maxParallel suggests, and the measurement contradicts the name, so state its scope rather than letting an operator infer it.

caveman has exactly two consumers: it rewrites the implementer brief, and it renders the local digest output terse. Reviewer and integrator dispatches carry no caveman path at all, so the reviewers — the largest emitters in a run — are unaffected by any value you set.

Read the full file on GitHub · 101 lines

Changes

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.

  1. 11d ago First seen · 101 lines · 24 tokens per session scan A d541e851e3d7

Subscribe to this mod's changes

teammates-config is a skill published in the GitHub repository andreymudri/claude-teammates (2 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 1,413 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

python-development

Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.

microsoft/agent-framework · 35 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens