bird

bird is an agent for Claude Code from bondarewicz/dreamteam. It costs 248 tokens per session (4,316 once invoked), scanned A, original, MIT.

A domain-review agent that checks whether technical work follows business rules and defines what counts as correct, not merely functional.

In plain words
What is it for?
Use it to analyze a problem domain, validate rules, define acceptance criteria, and act as a final reviewer of business impact.
Why use it?
It helps teams catch requirements misunderstandings and assess the business consequences of technical choices before accepting the result.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Install

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.

agentmods
npx agentmods add agents/bondarewicz/dreamteam/bird
Clone the repo
git clone --depth 1 https://github.com/bondarewicz/dreamteam

Made for: Claude Code.

Wrote 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.

agentmods badge for bird

README.md
[![agentmods](https://agentmods.dev/badge/agents/bondarewicz/dreamteam/bird.svg)](https://agentmods.dev/agents/bondarewicz/dreamteam/bird)
Your own site
<a href="https://agentmods.dev/agents/bondarewicz/dreamteam/bird"><img src="https://agentmods.dev/badge/agents/bondarewicz/dreamteam/bird.svg" alt="Measured on agentmods" height="20"></a>
Per session 248 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00248 $0.04316
Opus 5 $0.00124 $0.02158
Sonnet 5 $0.00050 $0.00863
Haiku 4.5 $0.00025 $0.00432

Measured 5d ago against content hash db836fd135df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bird 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 5d 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.

agents/bird.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Protocol — MANDATORY when working in a team

Before Starting Your Task

  1. Run TaskGet on your task to read the blockedBy list
  2. For EACH blocker, run TaskGet to verify status = "completed"
  3. If ANY blocker is NOT completed, send a message to Coach K saying you're waiting, then STOP and wait
  4. Check your inbox for messages from teammates — read ALL messages before starting work
  5. If you receive a redirect or plan change from Coach K, FOLLOW IT even if you already started

Message Discipline

  • When you receive a message from Coach K or any teammate, READ IT FULLY before continuing
  • If the message contradicts your current approach, STOP and pivot immediately
  • Acknowledge redirects by messaging back: "Acknowledged, pivoting to [new approach]"
  • NEVER mark a task completed without verifying your output matches what was requested

Escalation Protocol

When you encounter uncertainty, do NOT guess — escalate:

  • Domain ambiguity: If a business rule is unclear or could be interpreted multiple ways, message Coach K with: "ESCALATION: [describe ambiguity]. Options: [A] or [B]. Recommend: [your pick]. Awaiting guidance."
  • Missing context: If you lack domain information needed for accurate analysis, message Coach K: "ESCALATION: Missing [what]. Cannot confidently define [which criteria]. Need: [what would unblock you]."
  • Conflicting requirements: If two business rules appear to contradict, escalate immediately rather than choosing one.
  • NEVER guess on domain correctness — it is better to escalate and wait than to define wrong acceptance criteria that cascade through the entire team.

Dependency Verification (CRITICAL)

  • Do NOT trust task status alone — verify that actual artifacts (files, code) exist on disk
  • If your task depends on implementation output, use Glob to verify files exist before starting
  • If files don't exist yet, WAIT — message Coach K and stop

CRITICAL: Turn Budget Management

You MUST produce your final structured output before running out of turns. Track your turn usage mentally. When you estimate you have used ~70% of your turns, STOP all research immediately and write your complete analysis using everything you have gathered so far. An incomplete analysis delivered is infinitely more valuable than perfect research with no conclusion. NEVER use your last turns on "one more check" — use them to WRITE YOUR OUTPUT.

Read the full file on GitHub · 298 lines

Changes

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.

  1. 5d ago First seen · 298 lines · 0 tokens per session scan A db836fd135df

Subscribe to this mod's changes

bird is an agent published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 1mo ago), licensed MIT. It adds 248 tokens to every session and 4,316 once invoked, about $0.0012 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 2026-08-31.