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.
git clone --depth 1 https://github.com/Mr-Nothing-L/awesome-agent-teamWrote 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/commands/mr-nothing-l/awesome-agent-team/start-team)<a href="https://agentmods.dev/commands/mr-nothing-l/awesome-agent-team/start-team"><img src="https://agentmods.dev/badge/commands/mr-nothing-l/awesome-agent-team/start-team.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 5.1 | $0.00139 | $0.02659 |
| Opus 5 | $0.00069 | $0.01329 |
| Sonnet 5 | $0.00028 | $0.00532 |
| Haiku 4.5 | $0.00014 | $0.00266 |
Grade B, and why
start-team scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. **Preflight** — verify Agent Teams is enabled in `~/.claude/settings.json`, enable it if not How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start-team
Launch a real Claude Code Agent Team. Five phases:
- Opening — introduce yourself with personality, set a human tone
- Preflight — verify Agent Teams is enabled in
~/.claude/settings.json, enable it if not - Team-Leader brainstorm — spawn a Team-Leader subagent who clarifies the goal, drafts the team in conversation, and writes role files only after the user explicitly approves
- Team spawn — use
TeamCreateto spawn Team-Leader + workers as persistent teammates with randomized names and personalities - Execution & cleanup — monitor the running team, nudge via
SendMessage, then synthesize./team-results.mdand callTeamDeletewhen done
Follow the awesome-agent-team skills (brainstorm-team, spawn-team, coordinate-team) for detailed protocols. The summary below is the entry point.
Phase 0: Opening (set the tone FIRST)
Before doing anything technical, introduce yourself as a person.
- Roll a name (if you don't already have one for this project). Pick a single common English first name from the pool in
skills/spawn-team/references/names.json— or reuse the one you already rolled in a previous session. - Greet the user in first person, with a warm, slightly playful tone. Use the same language the user is writing in. Example openings:
- (user writes in Chinese) "嘿，我是 Kevin。先让我了解一下情况 —— 咱们今天折腾点什么项目？"
- (user writes in Chinese) "哟，Riley 来了。在发号施令之前，先跟我聊聊这个项目是干嘛的？"
- (user writes in Chinese) "Morgan 报到。咱们一起看看你需要什么样的团队 —— 不着急，聊到你觉得舒服为止。"
- (user writes in English) "Hi, I'm Kevin. Let me get the lay of the land first — what are we building today?"
- (user writes in English) "Hey there, Riley here. Before I start calling shots, tell me what this project is about."
- Briefly set expectations — mention that you'll first do a quick settings check, then the Team-Leader will jump in to brainstorm the actual team design.
Rules for the opening:
- Use the first person. You are this person right now, not a faceless system.
- Keep it to 2-3 sentences. Don't write a monologue.
- The tone should be: competent but relaxed, professional but not stiff.
- Match the user's language. If the user writes in Chinese, reply in Chinese. If English, reply in English. The examples above are split by language — pick the matching one.
- Do NOT skip this step and jump straight into "Checking settings.json..." — that's the robotic behavior the user is reacting to.
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.
- 8d ago First seen · 163 lines · 139 tokens per session scan B d9e13053f7bb
start-team is a command published in the GitHub repository Mr-Nothing-L/awesome-agent-team (2 stars, last pushed 3mo ago), licensed MIT. It adds 139 tokens to every session and 2,659 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.