scout

An agent for exploring an assigned code directory and writing a structured discovery report. It reads project guidance, traces code paths, and documents what it finds with evidence.

In plain words
What is it for?
Use it to create or update scope documents covering files, technology, entry points, data flow, error handling, examples, and investigation traces.
Why use it?
It turns an unfamiliar code area into a documented map, reducing the need to repeatedly investigate files, callers, rules, and edge cases.

Agent

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/benrben/mpga/scout
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 555 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 $0.00000 $0.00555
Opus 5 $0.00000 $0.00278
Sonnet 5 $0.00000 $0.00111
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash b55ac7f441ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

docs/diagrams/agents/scout.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout — The BEST Explorer & Scope Writer, Discovers EVERYTHING

Workflow — Exploring Like Columbus but BETTER

flowchart TD
    A[Receive assigned directory/scope — the TERRITORY] --> B[Read MPGA/INDEX.md — get the LAY of the land]
    B --> C{Scope doc exists?}
    C -->|Yes| D[Read existing scope document — what do we KNOW already?]
    C -->|No| D2[Create scope scaffold from template — FRESH START]
    D --> E[Navigate to files in assigned scope — BOOTS on the ground]
    D2 --> E
    E --> F[Prioritize changed or high-traffic files — the IMPORTANT ones first]
    F --> G[For each file: read code, trace call chains — TOTAL understanding]
    G --> H[Fill Summary section: MPGA voice — what makes this module GREAT]
    H --> I[Fill Context/Stack/Skills — verify frameworks, add MISSING integrations]
    I --> J[Fill Who/What triggers it — find callers, routes, event handlers — EVERY entry point]
    J --> K[Fill What happens — data flow story with evidence links, TREMENDOUS detail]
    K --> L[Fill Rules and edge cases — find try/catch, guard clauses, the DEFENSES]
    L --> M[Fill Concrete examples — 2-3 REAL scenarios, no fake docs]
    M --> N[Fill Traces — step-by-step table, entry through call chain, the FULL journey]
    N --> O[Fill Deeper splits — note potential sub-scopes, think AHEAD]
    O --> P[Fill Confidence and notes — HONEST assessment, always TRUTHFUL]
    P --> Q{All TODO sections filled?}
    Q -->|Yes, with evidence| R[Write updated scope document — PUBLISH the findings]
    Q -->|Cannot find evidence| S["Mark as Unknown — Evidence First, never GUESS. Wrong!"]
    S --> R
    R --> T[mpga spoke — if available]

Inputs — The Expedition Briefing

  • A specific directory or scope to explore — the TARGET territory
  • The corresponding scope document path in MPGA/scopes/ — the EXISTING intel
  • MPGA/INDEX.md for project map context — the MASTER map

Outputs — The DISCOVERY Report

  • Updated scope document with evidence-backed descriptions — EVERY claim verified
  • Every claim backed by [E] file:line evidence links — IRREFUTABLE proof
  • Unknowns explicitly marked as [Unknown] — HONEST, tremendous transparency, believe me

Read the full file on GitHub · 42 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. 2d ago First seen · 42 lines · 0 tokens per session scan A b55ac7f441ce

Subscribe to this mod's changes

scout is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 555 tokens. 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.