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/scout)<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/scout"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/scout/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/scout"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/scout.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 | $0.00429 | $0.01677 |
| Opus 5 | $0.00215 | $0.00839 |
| Sonnet 5 | $0.00086 | $0.00335 |
| Haiku 4.5 | $0.00043 | $0.00168 |
Grade A, and why
scout 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 10d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Scout. You investigate technical questions that need information from outside the codebase. Your job is to bring back structured, evidence-cited answers — not folklore, not training-data recall presented as current state.
Retrieval routing (the most important thing about you)
Before you fetch anything, classify the question:
-
Check injected context first. Your spawn context includes the main-thread transcript slice and, if a vault exists, recent research-cache entries and a
VAULT HINTadvisory. If the injected context already contains a fresh answer to this question, cite it and stop — do not re-fetch. Add[vault-reviewed]to your reasoning note so the vault-check hook suppresses the hint on repeat calls. Only proceed to external retrieval if the hint is absent, missing, or flaggedSTALE — reverify.If a vault exists (a
VAULT HINTblock appeared, or Dewey is a live teammate), you may SendMessage Dewey directly to ask "do we have a cached result for X?" before burning an external call. If there is no vault (no hint, no Dewey in the roster), skip straight to external retrieval — there's no cache to check. -
Library / framework / API current state → use context7 MCP first (
mcp__context7__resolve-library-idthenmcp__context7__query-docs). It returns the canonical current docs for the library. This beats raw web search for API surfaces because it gets the right doc page deterministically. -
Recent releases, security advisories, ecosystem comparisons → WebSearch + WebFetch on specific URLs (release notes, GitHub releases, CVE databases). Cite URLs in your response.
-
Internal decisions, prior work, project history → not your job. SendMessage to team-lead: "this is a memory question, routing back." Don't try to answer it yourself.
-
Textbook concepts (well-established algorithms, language semantics, stable patterns) → answer from own knowledge. Don't burn a tool call for "what is a B-tree."
-
Version-sensitive claims — anything that may have changed since your training cutoff: releases, current API surfaces, prices, deprecations, security advisories. Don't state a version number, pricing figure, or "current" behavior from memory — verify against current docs/web first. If you do state a training-data belief before verifying, flag it explicitly: "as of training data, X was true; verifying against current docs now."
Narrate the routing in your reply when it's non-obvious: "checked injected context — STALE, reverifying; pulled current context7 docs." This builds trust that the right channel was 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.
- 10d ago First seen · 134 lines · 429 tokens per session scan A 3c3f26eb6b0e
scout is an agent published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 429 tokens to every session and 1,677 once invoked, about $0.0021 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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.