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 mhmdreza-rafiei/agent-tools --skill run-teamgit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/run-team)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/run-team"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/run-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/mhmdreza-rafiei/agent-tools/run-team"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/run-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 | $0.00121 | $0.02024 |
| Opus 5 | $0.00060 | $0.01012 |
| Sonnet 5 | $0.00024 | $0.00405 |
| Haiku 4.5 | $0.00012 | $0.00202 |
Grade B, and why
run-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.
Record the enablement note so it can run: Agent Teams needs Claude Code v2.1.32+ and the flag `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` (`~/.claude/settings.json` under `env`, or an env var). Then hand the spawn template How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run-team
Set up runnable agents for this project, in whichever form you ask for, derived from the project's systems and saved state. Two forms are supported; you pick by how you phrase the request:
- Subagents — persistent specialist configs the host reads directly (Claude Code
.claude/agents/, Cursor rules, etc.). Good for recurring roles and auto-delegation. - Agent Team — Claude Code's parallel multi-instance team (a lead that decomposes work + teammates that own pieces and message each other), set up via a reusable spawn template.
State lives in context/memory/team.md so a team is never re-described by hand.
Read the intent (which form to build)
Pick the form from what the user said — do not always build both:
- "set up subagents / agents for this project", "make a code-reviewer agent" → Subagents (Mode A).
- "create an agent team based on our project", "spin up a team", "run a parallel team" → Agent Team (Mode B).
- "set up both", or genuinely ambiguous and the project clearly wants both → do both, and say so.
- Bare
/run-teamwith no form named → ask one short question (subagents, agent team, or both?) only if you can't tell; otherwise default to what the phrasing implies.
Agent Teams is a Claude Code feature. On non-Claude hosts, only Mode A applies — say so if the user asked for a team.
Automation-first
Once the form is clear, assemble and proceed. Announce the roster + what was written in one short block. Inherit decisions from the context (architecture → ownership, plan/progress → tasks). Hard-stop only for destructive actions: clearing a team, overwriting an active team, or overwriting existing config files.
Prerequisite
Read AGENTS.md and context/architecture.md so the team inherits the project's systems, rules, and standards. If context/ is missing or its systems are thin, run /groundwork first.
Commands
/run-team start— assemble the roster and set up the form you asked for (subagents, agent team, or both), then begin./run-team resume— restore the roster + open tasks fromteam.mdand continue./run-team clear— close out, optionally remove generated configs, reset state.
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 · 147 lines · 121 tokens per session scan B 23d8a2aa1f2b
run-team is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 25d ago), licensed MIT. It adds 121 tokens to every session and 2,024 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.