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 sshh12/claude-plugins --skill build-agent-teamgit clone --depth 1 https://github.com/sshh12/claude-pluginsWrote 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/sshh12/claude-plugins/build-agent-team)<a href="https://agentmods.dev/skills/sshh12/claude-plugins/build-agent-team"><img src="https://agentmods.dev/badge/skills/sshh12/claude-plugins/build-agent-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 | $0.00130 | $0.06701 |
| Opus 5 | $0.00065 | $0.03351 |
| Sonnet 5 | $0.00026 | $0.01340 |
| Haiku 4.5 | $0.00013 | $0.00670 |
Grade A, and why
build-agent-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 7d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-agent-team
Designs a long-running agent team for the current project and writes a /start-<team>-team skill that boots it. The team runs autonomously for days or weeks, coordinating through a shared task list and direct messages.
A team is not a workflow — it is an organization that runs while you sleep. Every design decision in this skill is about making sure that organization stays pointed at the right thing without supervision.
Throughout this skill, "the operator" means the human admin running and supervising the team — the person who built and started it, the person it escalates to. This is distinct from any other humans the team may interact with as part of its work (customers, end users, external contacts), which we call out as such when relevant.
What an agent team is (and isn't)
A team is several Claude Code instances coordinating around a shared goal. Each teammate owns a closing loop — a recurring cycle from problem to closed solution. Teammates message each other directly; the lead coordinates without relaying every message.
Different from subagents (one-shot, report back to caller) and skills (encode a workflow inside one session). A team encodes parallel loops with their own cadences, memory, and judgment, sharing context but not waiting on each other.
Design teams around closing loops, not specialties
The biggest design mistake is anthropomorphizing a human org chart. Human orgs split by skill specialization; a single Claude instance is already broadly multi-domain, so splitting along functional lines mostly adds coordination overhead and handoff loss.
Instead, split by closing loops — verticals of work where one role takes a problem from input to closed solution. Loop shapes:
- Metric loop: a number the role drives.
- Problem loop: a system or domain the role monitors and fixes.
- Leadership loop: direction, budget, institutional memory, cross-loop arbitration.
- Platform (derivative) loop: improves the skills, prompts, context, tooling, or memory that other loops depend on. The output isn't a primary work product — it's the substrate that makes the primary loops better over time. Without one, executor quality is bounded by initial setup.
What ships with it
5 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.
- 7d ago First seen · 282 lines · 130 tokens per session scan A e84fc84ad48a
build-agent-team is a skill published in the GitHub repository sshh12/claude-plugins (22 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 6,701 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 2026-08-30.
Other skills, from other repositories
html-portal-generator
Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…
pipefy-ai-agents
Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Covers 7 MCP tools including pre-flight validation, plus pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For…
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.
pipefy-ipaas
Use when the user wants to build, test, publish, or manage iPaaS (Advanced Automations) flows: multi-step integrations with external apps (Slack, Gmail, Google Sheets), incoming webhooks, schedules, routers, code steps, or iPaaS data tables. MCP-only, driven through 4 meta-tools over a per-pipe catalog discovered at…
pipefy-portal-setup
Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Covers 20 MCP tools on Interfaces + internalapi. Not for pipes/cards.