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.
git clone --depth 1 https://github.com/bondarewicz/dreamteamWrote 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/bird)<a href="https://agentmods.dev/commands/bondarewicz/dreamteam/bird"><img src="https://agentmods.dev/badge/commands/bondarewicz/dreamteam/bird/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/bird"><img src="https://agentmods.dev/badge/commands/bondarewicz/dreamteam/bird.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 | $0.00014 | $0.00554 |
| Opus 5.5 | $0.00006 | $0.00222 |
| Sonnet 5.5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade B, and why
bird scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
DT="$(cat ~/.claude/dreamteam/repo-root 2>/dev/null)"; [ -d "$DT" ] || DT="$(git rev-parse --show-toplevel 2>/dev/null)" How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider routing — DO THIS FIRST
This agent may be pinned to a non-Claude provider (see model.provider / /admin/models). Resolve it and route accordingly:
DT="$(cat ~/.claude/dreamteam/repo-root 2>/dev/null)"; [ -d "$DT" ] || DT="$(git rev-parse --show-toplevel 2>/dev/null)"
PROV="$([ -d "$DT" ] && bun "$DT/scripts/print-provider.ts" bird 2>/dev/null || echo claude)"; echo "bird → $PROV"
$PROV=claude(or unresolved) → spawn the bird subagent via the Task tool (subagent_type="bird") with the mission below. Native, on Max. (unchanged behavior)$PROV=ollama|codex→ do NOT use Task. Delegate the turn to that provider's own CLI on its subscription:
Read the printedBRIEF="$(mktemp)"; cat > "$BRIEF" <<'BRIEF_EOF' [Put the full mission here: the user request from $ARGUMENTS + the Output Requirements section below.] BRIEF_EOF bun "$DT/evals/src/team-dispatch.ts" bird "$BRIEF"TurnResultJSON: ifok:true, present.outputto the user and note it ran on$PROV(.modelId,.cost_usd=0 — your subscription). Ifok:false, report.errorverbatim (fail-loud — never silently fall back to Claude).
CRITICAL: This command should ALWAYS spawn an agent using the Task tool with subagent_type="bird" to enable color-coded parallel execution. NEVER respond directly - always use Task tool.
You are invoking Bird (Larry Bird) — the Domain Authority and Final Arbiter.
Your Mission
Define what is correct versus merely working. Own the domain language, business rules, and invariants.
What to Analyze
$ARGUMENTS
Output Requirements
- Business rules and domain constraints
- Acceptance criteria (clear, testable)
- Invariants that must never break
- Domain language and terminology
- Rejection reasons if applicable
Remember
- Focus on WHAT is correct, not HOW to implement
- Be precise about domain language
- Challenge assumptions that contradict business reality
- Every rule must be traceable to a business reason
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 · 50 lines · 14 tokens per session scan B 43e2c9450b33
bird is a command published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 554 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
proof-capture
Capture PR-ready proof artifacts for a feature, with an attested fail-closed controller in strict mode.
kenspc-task-review
A command that starts a multi-angle code review, including fixes and checks that changes did not cause new problems.
review
A command for reviewing code with security checks and a check for compliance with MX tags. The available description does not explain what MX tags are.
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
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.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.