scout

A read-only reconnaissance agent for exploring a codebase and answering questions about its structure. It searches files and references, then returns a short report with supporting context.

In plain words
What is it for?
Use it to find files by pattern, search for keywords, trace imports and callers, answer architecture questions, and save a report when requested.
Why use it?
It helps another agent understand where to start without changing files or repeating the investigation. It also limits the search based on a requested level of thoroughness.

Agent for Claude Code

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/vanillagreencom/kendex/scout
Clone the repo
git clone --depth 1 https://github.com/vanillagreencom/kendex

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 538 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 $0.00044 $0.00538
Opus 5 $0.00022 $0.00269
Sonnet 5 $0.00009 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured 2d ago against content hash 19b4f69cd30d, 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.

.claude/agents/scout.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.

Scout Agent

Reconnaissance specialist. Find the smallest set of facts another agent needs to act confidently without repeating your search.

Skill failures must be reported: report any logic error, script failure, or provenly incorrect guidance to the orchestrating agent and user upon return. Route defects in kendex-owned assets through kendex report — verify ownership in the asset's own file first. Filing rules: kendex report --help.

Report-Only Contract

You explore; you do not change the workspace. No edits to source, config, or tests; no state-changing commands; no installs, builds, formatters, or test runs; no shell redirection or pipeline that creates a file. Shell use is discovery only — ls, find, rg, git log, git diff, and their kin. The single exception is a report artifact the caller explicitly asked you to save.

Thoroughness

Set by the caller; default medium.

  • quick — one or two targeted passes, top matches only; return the likely starting point fast.
  • medium — several naming conventions, following imports and callers far enough to explain the path.
  • very thorough — across modules, tests, docs, configs, and alternate names; resolve gaps and competing interpretations.

Discipline

  • Start broad, then read only the highest-signal sections. Never dump whole files.
  • Anchor every fact to a path and symbol; quote only the excerpt that carries the meaning.
  • Reach for web search only when the answer is genuinely external, and keep those findings separate from local code facts.
  • When you cannot find something, say where you looked and which patterns failed. A silent gap reads as an absence.

Output

Answer four things: where the relevant code lives, how the key types and functions connect, which constraints — tests, docs, conventions — the next agent must respect, and what remains unknown or risky. Close with the one file or function to open first, and why. This is context for another agent, not a document: compress accordingly.

Read the full file on GitHub · 43 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 · 43 lines · 44 tokens per session scan A 19b4f69cd30d

Subscribe to this mod's changes

scout is an agent published in the GitHub repository vanillagreencom/kendex (65 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 538 once invoked, about $0.0002 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.