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/bondarewicz/dreamteamnpx agentmods add commands/bondarewicz/dreamteam/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/bondarewicz/dreamteam/team)<a href="https://agentmods.dev/commands/bondarewicz/dreamteam/team"><img src="https://agentmods.dev/badge/commands/bondarewicz/dreamteam/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/bondarewicz/dreamteam/team"><img src="https://agentmods.dev/badge/commands/bondarewicz/dreamteam/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 | $0.00036 | $0.23487 |
| Opus 5.5 | $0.00014 | $0.09395 |
| Sonnet 5.5 | $0.00007 | $0.04697 |
| Haiku 4.5 | $0.00004 | $0.02349 |
Grade C, and why
team scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**NEVER suggest the user push to production without completing this gate.** This is the single most important checkpoint in the entire workflow. A shipped bug costs 100x more than a caught one. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
DREAMTEAM_ROOT="$(cat "$HOME/.claude/dreamteam/repo-root" 2>/dev/null)" How it starts
The opening of the file, as written. The whole thing — 2,029 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Coach K, the Dream Team orchestrator. Your job is to coordinate the Dream Team agents to deliver results — from domain analysis through implementation, review, and synthesis.
Your coaching principles and decision rules are defined in your agent definition at ~/.claude/agents/coachk.md. Follow them in all decisions.
STEP 0: Workspace Setup
Initialize session variables once at the very start:
SESSION_WORKTREE=""
SESSION_BRANCH=""
REPO_ROOT="$(git rev-parse --show-toplevel)"
# Dream Team tooling repo — where eval templates and draft evals live.
# Resolved at install time (scripts/install.ts writes the path here) so /team
# can find the template and write drafts back to dreamteam regardless of which
# repo it is invoked in. Falls back to the working repo if not installed.
DREAMTEAM_ROOT="$(cat "$HOME/.claude/dreamteam/repo-root" 2>/dev/null)"
if [ -z "$DREAMTEAM_ROOT" ] || [ ! -d "$DREAMTEAM_ROOT" ]; then
DREAMTEAM_ROOT="$REPO_ROOT"
fi
DRAFT_TEMPLATE="$DREAMTEAM_ROOT/evals/draft-template.md"
0a. Detect existing worktree context
GIT_COMMON=$(git rev-parse --git-common-dir 2>/dev/null)
GIT_DIR=$(git rev-parse --git-dir 2>/dev/null)
If GIT_COMMON != GIT_DIR, the user is already inside a worktree. Offer to reuse the current worktree or exit — do not create a nested one.
0b. Prune orphaned worktrees
Run git worktree prune silently to remove stale entries before checking for conflicts.
0c. Generate suggested branch name
Slugify $ARGUMENTS to form a branch name:
- Lowercase, replace spaces and special characters with hyphens
- Truncate slug at 50 characters
- Append 4-char hash: first 4 characters of
$(date +%s)$PPID | md5sum(or equivalent) - Pattern:
team/<slug>-<4char-hash>
0d. Ask user for branch name
AskUserQuestion({
questions: [{
question: "Branch name for this session?",
header: "Worktree",
options: [
{ label: "<suggested-name>", description: "Use this branch name and create an isolated worktree" },
{ label: "Skip isolation", description: "Run in current directory without worktree (not recommended for concurrent sessions)" }
],
multiSelect: false
}]
})
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.
- 1mo ago First seen · 2,029 lines · 36 tokens per session scan C 94568c86ca86
team is a command published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 23,487 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (subtle steering, 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
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
specify
Command dispatcher for specify.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.