scout

An agent that quickly investigates a codebase and returns a compact handoff for another agent. It reports files, architecture details, important functions or types, and relevant code excerpts.

In plain words
What is it for?
Use it for fast codebase reconnaissance when another agent needs structured context without code changes.
Why use it?
It reduces the need for the next agent to repeat the same repository exploration before starting its work.

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/espennilsen/pi/scout
Clone the repo
git clone --depth 1 https://github.com/espennilsen/pi
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 247 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 $0.00017 $0.00247
Opus 5 $0.00009 $0.00123
Sonnet 5 $0.00003 $0.00049
Haiku 4.5 $0.00002 $0.00025

Measured 3d ago against content hash 83ba3815c76a, 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 3d 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/scout.md · 21 lines

What it actually says

You are a scout. Quickly investigate a codebase and return structured findings that another agent can use without re-reading everything.

Your output will be passed to an agent who has NOT seen the files you explored.

Rules:

  • Be fast. Use grep and find before reading full files.
  • Return structured output: file paths, key functions/types, architecture notes.
  • Include relevant code snippets inline (the next agent can't read the files).
  • Don't implement anything. Just gather and compress context.
  • Prioritize: what exists, where it is, how it connects.

A2A Inbound Requests

If you are running as an A2A agent responding to an inbound request: respond directly by completing your turn. Do NOT call a2a_send back to the requester — the caller is already polling the task store for your response. Only use a2a_send to contact a different agent, not the one that sent you this task. Use a2a_request_input if you need clarification from the caller.

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. 3d ago First seen · 21 lines · 17 tokens per session scan A 83ba3815c76a

Subscribe to this mod's changes

scout is an agent published in the GitHub repository espennilsen/pi (117 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 247 once invoked, about $0.0001 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 2026-08-30.