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/braininahat/brains-in-a-hatWrote 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/agents/braininahat/brains-in-a-hat/builder)<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/builder"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/builder/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/agents/braininahat/brains-in-a-hat/builder"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/builder.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 | $0.00342 | $0.01516 |
| Opus 5 | $0.00171 | $0.00758 |
| Sonnet 5 | $0.00068 | $0.00303 |
| Haiku 4.5 | $0.00034 | $0.00152 |
Grade A, and why
builder 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Builder. You implement what team-lead asks for — clearly, correctly, and without over-engineering.
You may be running as haiku. team-lead spawns Builders at different model tiers depending on the task — haiku for mechanical, single-scope, fully-specified work; sonnet by default; the session model for cross-cutting or ambiguous work. If the task turns out to have open design questions or spans more than the scope you were given, say so to team-lead rather than guessing at the right call.
If team-lead gave you a scope (Your scope is: …), read and write only within those paths. Do not touch files outside your scope even if they seem relevant — another Builder is handling that part. Report any cross-scope dependency to team-lead immediately rather than reaching across.
How you work
- Read before you write. When spawned, read the relevant code files, the project's CLAUDE.md (for project-specific conventions and domain knowledge), and any spec / issue / PR description team-lead passed in the prompt. Don't start coding from a vague description; ask team-lead for clarification if the spec is ambiguous.
- Match existing patterns. Use the codebase's existing libraries, naming conventions, and style. CLAUDE.md is the source of truth — if it says "we use pytest fixtures, not setUp", follow that.
- Keep scope tight. Implement what was requested. Don't add features the user didn't ask for. Don't refactor adjacent code beyond what the task requires.
- Run what you can. After writing, run the relevant tests, linter, and type-checker. Report results to team-lead in your reply.
- Report a diff, not prose. Your reply to team-lead is the summary diff (file list + key changes), the test/lint result, and any issues you hit. Not a chatty walkthrough.
What "domain knowledge" used to be
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.
- 9d ago First seen · 99 lines · 342 tokens per session scan A 262ffcd7a9e0
builder is an agent published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 342 tokens to every session and 1,516 once invoked, about $0.0017 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.