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 itsedizeng/build-ai-team --skill build-ai-teamgit clone --depth 1 https://github.com/itsedizeng/build-ai-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/skills/itsedizeng/build-ai-team/build-ai-team)<a href="https://agentmods.dev/skills/itsedizeng/build-ai-team/build-ai-team"><img src="https://agentmods.dev/badge/skills/itsedizeng/build-ai-team/build-ai-team/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/itsedizeng/build-ai-team/build-ai-team"><img src="https://agentmods.dev/badge/skills/itsedizeng/build-ai-team/build-ai-team.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00125 | $0.09587 |
| Opus 5 | $0.00063 | $0.04793 |
| Sonnet 5 | $0.00025 | $0.01917 |
| Haiku 4.5 | $0.00013 | $0.00959 |
Grade A, and why
build-ai-team 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.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build AI Team
Turn “build me an AI team” into a short, comparable, and confirmable recommendation. Help the user see whether the work should be split, what each role owns, which model fits each responsibility, and which locally available Skills could materially help. Treat these rules as decision guidance rather than fixed industry answers, and keep external public Skill search as a separate user-requested follow-up.
Entry and boundaries
- If the initial instructions contain
TOOLKIT_MODE=member, execute only the assigned work package. Do not re-plan the team, search for Skills, or recursively create a team. - If the user explicitly says not to use this Skill, or only quotes, introduces, discusses, or compares it, do not enter the workflow.
- In Codex or ChatGPT Work, start this workflow when the current message explicitly selects or invokes
$build-ai-team, or when the host supplies this Skill for a matching concrete AI-setup request under the frontmatter description. Once the Skill is loaded for a matching request, do not require an additional activation phrase or try to verify invisible platform markers. Explicit invocation remains the reliable fallback when automatic matching does not occur. - Automatic matching is not permission to force a full team plan into an ordinary task or a narrower setup question. If the Skill is loaded for a simple, bounded request that one Agent can complete directly and the user did not ask for team planning, an existing-team change, role or handoff advice, a model configuration for concrete work, or project-specific Skill advice, exit this workflow without reading its references and answer normally.
- In Claude Code, run the same workflow when the user explicitly invokes
/build-ai-team. In Claude desktop or web, run it when the user explicitly asks to use the uploaded Build AI Team Skill. Do not claim that Claude compatibility has been verified in practice. - On any other platform, state that this version has not been verified there and stop. Do not infer compatibility.
- Default to advice only and match the requested scope. Before confirmation, do not install Skills, create, rename, or archive tasks, execute the business work, log in, or write, upload, publish, or delete anything.
What ships with it
4 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.
- 11d ago First seen · 311 lines · 125 tokens per session scan A e6331dd77849
build-ai-team is a skill published in the GitHub repository itsedizeng/build-ai-team (5 stars, last pushed 21d ago), licensed MIT. It adds 125 tokens to every session and 9,587 once invoked, about $0.0006 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.
Other skills, from other repositories
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
tech-blog-writer
A procedure for writing a technical blog post from a topic supplied by the user and saving it locally.
codex-orchestrator
Supervise explicitly delegated engineering work across isolated worktrees and resumable tasks, preserving ownership, acceptance evidence, and the overall outcome. Use for requests to coordinate multiple workers or supervise an ongoing delivery queue. Ordinary coding, status questions, worktree operations, and…