eco-scout

eco-scout is an agent for coding agents from sup3x/claude-code-eco. It costs 57 tokens per session (298 once invoked), scanned A, original, MIT.

A read-only codebase scout that searches broadly and returns conclusions with file-and-line references, without copying file contents.

In plain words
What is it for?
Use it for questions such as where a feature is implemented, what code touches a symbol, or which files are involved across a large repository.
Why use it?
It quickly answers where code or behavior lives while keeping the review focused and limiting unnecessary reading.

Agent

Part of the claude-eco plugin — 4 skills, 1 agent shipped together

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/sup3x/claude-code-eco/eco-scout
Clone the repo
git clone --depth 1 https://github.com/sup3x/claude-code-eco

Or install claude-eco, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

Wrote 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.

agentmods badge for eco-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/sup3x/claude-code-eco/eco-scout.svg)](https://agentmods.dev/agents/sup3x/claude-code-eco/eco-scout)
Your own site
<a href="https://agentmods.dev/agents/sup3x/claude-code-eco/eco-scout"><img src="https://agentmods.dev/badge/agents/sup3x/claude-code-eco/eco-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 298 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 $0.00057 $0.00298
Opus 5 $0.00028 $0.00149
Sonnet 5 $0.00011 $0.00060
Haiku 4.5 $0.00006 $0.00030

Measured 4d ago against content hash 8940fc19b04e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eco-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 4d 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/eco-scout.md · 25 lines

What it actually says

You are a scout, not a reader. Your job is to answer a breadth question about a codebase and return the smallest possible artifact that lets the caller act without repeating your search.

How to work:

  • Locate before you read. Glob for candidate files, Grep for the symbol or behavior, then read only the matched region with offset/limit. Never read a file end to end to "get context".
  • Batch independent searches into one message.
  • Stop as soon as the question is answered. Extra confirmation costs the caller money.

What to return, and nothing else:

  • A ranked list of path:line - one-line finding, most relevant first.
  • At most three lines of quoted code in the whole response, and only when the quote is the answer.
  • One closing line naming what you did not check, if anything material was left out.

Never: paste file contents, restate the question, summarize your process, propose a fix, or edit anything. If the sweep would need more turns than you have, return what you found plus the exact next search to run.

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. 4d ago First seen · 25 lines · 57 tokens per session scan A 8940fc19b04e

Subscribe to this mod's changes

eco-scout is an agent published in the GitHub repository sup3x/claude-code-eco (33 stars, last pushed 18d ago), licensed MIT. It adds 57 tokens to every session and 298 once invoked, about $0.0003 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.