Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dyCuong03/unity-agent-teamnpx agentmods add commands/dycuong03/unity-agent-team/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/dycuong03/unity-agent-team/team)<a href="https://agentmods.dev/commands/dycuong03/unity-agent-team/team"><img src="https://agentmods.dev/badge/commands/dycuong03/unity-agent-team/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/commands/dycuong03/unity-agent-team/team"><img src="https://agentmods.dev/badge/commands/dycuong03/unity-agent-team/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 | $0.00070 | $0.10108 |
| Opus 5.5 | $0.00028 | $0.04043 |
| Sonnet 5.5 | $0.00014 | $0.02022 |
| Haiku 4.5 | $0.00007 | $0.01011 |
Grade B, and why
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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -q '"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"[[:space:]]*:[[:space:]]*"1"' ~/.claude/settings.json \ How it starts
The opening of the file, as written. The whole thing — 866 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/team — Adaptive Unity DOTS Pipeline
/team <intent> [depth] <task description>
/team --team <task description> # deprecated alias: --full
intent ∈ { bug, feature, refactor, explore }
depth ∈ { quick, normal, deep } default: normal
Two modes:
| Mode | Command | Behavior |
|---|---|---|
| Adaptive (default) | /team <intent> [depth] <task> |
Triage → minimum agents → artifact-gated (in-process subagents) |
| Team | /team --team <task> (deprecated alias --full) |
Claude Agent Teams — current session is teamlead; persistent teammates from config teamProfiles.full on Sonnet (NOT subagents, NOT simulated, NOT tmux/worktree) |
| Worktrees | /team --worktrees <task> |
Advanced opt-in: manual tmux + git-worktree team via full_team.py |
STEP -1 — Resolve project context (ALL modes, before anything else)
Run the unified resolver once at the start of every /team invocation:
python3 .claude/scripts/roots.py --json
All subsequent paths come from this output — never from assumptions about cwd, repo name, or layout:
workspaceDir→ everyworkspace/...path mentioned in this commandreportsDir→ everyreports/...pathworktreeRoot→ worktree locations (--worktreesmode)defaultBranch→ base branch for worktree branches and mergesPROJECT_ROOT,projectType,UNITY_PROJECT_ROOT,projectName,teamProfiles→ injected into every agent/teammate prompt
If roots.py errors, STOP and tell the user to run
python3 .claude/scripts/setup.py, then re-run /team.
roots.py exits 0 with built-in defaults when no project-config.json
exists — so ALSO check the output: if configPath is null, the project has
not been set up. STOP and instruct the user to run
python3 .claude/scripts/setup.py (defaults like teamProfiles and
projectType=generic are placeholders, not a configured project).
The adaptive path always runs triage first, always calls
orchestrate.py plan to derive the pipeline, and never spawns agents that
the plan does not list. Every phase boundary is a Python gate; if the gate
exits non-zero, you halt — no exceptions, no markdown promises.
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 · 866 lines · 70 tokens per session scan B 9f4d444ad700
team is a command published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 10,108 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
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).
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
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.