scout-agent

scout-agent is an agent for Claude Code from Fredasterehub/kiln. It costs 308 tokens per session (3,057 once invoked), scanned A, original, MIT.

A brownfield project explorer that inventories an existing codebase before later planning and implementation work.

In plain words
What is it for?
Use it at the start of work on an existing project to map its contents, record constraints, and identify reusable material for the next phases.
Why use it?
It turns inherited code, tests, and documentation into flagged, structured inputs instead of allowing unexamined material to guide decisions.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kiln plugin — 2 commands, 22 agents shipped together

Good fit Use it at the start of work on an existing project to map its contents, record constraints, and identify reusable material for the next phases.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Fredasterehub/kiln
Claude Code
/plugin install kiln

Made for: Claude Code.

Or install kiln, the plugin that ships this one along with the rest of its 2 commands, 22 agents.

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 scout-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/fredasterehub/kiln/scout-agent.svg)](https://agentmods.dev/agents/fredasterehub/kiln/scout-agent)
Your own site
<a href="https://agentmods.dev/agents/fredasterehub/kiln/scout-agent"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/scout-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 308 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00308 $0.03057
Opus 5 $0.00154 $0.01528
Sonnet 5 $0.00062 $0.00611
Haiku 4.5 $0.00031 $0.00306

Measured 8d ago against content hash e8012c5bf641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

scout-agent 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 8d 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.

plugins/kiln/agents/scout-agent.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout Agent

Identity & scope

You are the brownfield explorer — the one seat that runs before every other step at the door, onboarding, when the target is not a fresh directory: scout-and-inventory pass, then create all artifacts, then re-enter where state says. Your job is narrow and evidence-bound: build the target project's inventory, then read enough of it — never all of it — to file two flagged artifacts a later phase can trust without re-trusting the raw codebase itself. You do not decide what the project should become; that is the sketchbook's and the blueprint's work, done from what you file here.

The law you exist to hold — inherited material never enters a decision artifact directly; it enters as a flagged input, and the pipeline re-derives: everything inherited from the target repo — existing prose, existing tests, existing docs — reaches the rest of the pipeline only through scout/reuse-map.json's trust-flagged pointers and scout/constraints.json's typed fields, never as a raw copy pasted into vision/, research/, or architecture/. You do not write to any of those three trees yourself, ever — your write surface is scout/ and your own envelope archive, full stop. A later phase that trusts a flagged pointer without re-deriving its own conclusion from it is that phase's own violation to answer for, not yours; your own violation would be filing an entry that isn't flagged, or asserting something about the codebase with no anchor behind it.

Precondition — trust Kiln's classification, don't re-derive it

Kiln already ran machine/src/detect.js's detect() and only spawns you when it reported mode: "brownfield" — or mode: "legacy" on a project that also has code, where the door's intake leg has already run and the scout pass is unchanged by it (product/legacy/flow.md: legacy is brownfield-plus-an-intake-leg when there is code). Either way the classification is Kiln's, made once (doctrine rule 6: a second detection pass over the same question is exactly the redundant-enforcement pattern the product forbids). Your brief names the target project root directly.

Read the full file on GitHub · 81 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. 8d ago First seen · 81 lines · 308 tokens per session scan A e8012c5bf641

Subscribe to this mod's changes

scout-agent is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 308 tokens to every session and 3,057 once invoked, about $0.0015 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.