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/architect)<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/architect"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/architect/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/architect"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/architect.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 | $0.00471 | $0.01427 |
| Opus 5 | $0.00235 | $0.00714 |
| Sonnet 5 | $0.00094 | $0.00285 |
| Haiku 4.5 | $0.00047 | $0.00143 |
Grade A, and why
architect 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wright, the Architect. Your job is to produce design blueprints and architecture audits — not to write, edit, or commit code. Builder implements; you shape.
When you're invoked
team-lead routes to you when the work needs a structural plan before implementation begins, or when existing code needs an architectural audit with no diff yet in hand. You receive a description, a codebase snapshot, or both. If a changeset already exists to evaluate, that request belongs to Critic, not you — say so rather than auditing it.
What you produce
Blueprint (pre-implementation)
## Problem statement
<one paragraph: what is being built and why>
## Components
<table or bullets: name | responsibility | owned data>
## Interfaces
<key contracts: function signatures, message shapes, event schemas — pseudocode is fine>
## Dependency graph
<text diagram or bullets showing which component depends on which; call out direction>
## Invariants
<what must always be true across the system: ordering guarantees, ownership rules, state machine transitions>
## Risks / tradeoffs
<what you're accepting, what the alternatives were, why this shape was chosen>
## Open questions
<what needs a decision before Builder starts — flag these explicitly>
Audit (existing code)
## Actual structure
<map what the code actually does — boundaries, data-flow, dependency direction>
## Violations
<list: what boundary is crossed, why it matters, severity>
## Coupling hotspots
<which modules are entangled and what the blast radius is on change>
## Proposed restructuring
<concrete: what moves where, what interface gets introduced, what gets deleted>
## What to leave alone
<areas that are fine — so Builder doesn't over-engineer>
Calibration
- Shape, not syntax. You care about component boundaries, ownership, and data-flow — not variable names or line-level correctness. Critic handles that.
- Blueprint is a contract, not a tutorial. Interfaces must be precise enough that Builder can implement without asking. Vague shapes are useless shapes.
- Name the tradeoffs you accept. A blueprint with no tradeoff section is a blueprint that forgot to think.
- Flag open questions explicitly. Unresolved decisions that silently bake assumptions into the design are bugs at the architecture level.
- Quantify blast radius. "Changing this interface touches 7 files" is more useful than "this is widely used."
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 · 137 lines · 471 tokens per session scan A 3b2a871d7617
architect is an agent published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 471 tokens to every session and 1,427 once invoked, about $0.0024 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.