surveyor

surveyor is an agent for coding agents from lucasacoutinho/dds. It costs 42 tokens per session (2,185 once invoked), scanned A, original, MIT.

An agent that quickly maps an unfamiliar or older codebase without reading every line. It identifies the technology stack, modules, entry points, deployment details, and likely analysis effort, with evidence from project files.

In plain words
What is it for?
Use it for the first phase of legacy-system analysis. It can produce spec/00-survey.md with the stack, module map, entry points, deployment topology, and estimated excavation cost.
Why use it?
It provides a reliable high-level view before deeper code investigation begins. Its evidence-based approach helps avoid guessing which frameworks or components the project contains.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the dds plugin — 3 skills, 8 agents 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/lucasacoutinho/dds/surveyor
Clone the repo
git clone --depth 1 https://github.com/lucasacoutinho/dds

Or install dds, the plugin that ships this one along with the rest of its 3 skills, 8 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 surveyor

README.md
[![agentmods](https://agentmods.dev/badge/agents/lucasacoutinho/dds/surveyor.svg)](https://agentmods.dev/agents/lucasacoutinho/dds/surveyor)
Your own site
<a href="https://agentmods.dev/agents/lucasacoutinho/dds/surveyor"><img src="https://agentmods.dev/badge/agents/lucasacoutinho/dds/surveyor.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,185 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 $0.00042 $0.02185
Opus 5 $0.00021 $0.01092
Sonnet 5 $0.00008 $0.00437
Haiku 4.5 $0.00004 $0.00218

Measured 5d ago against content hash daa3eadf43cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

surveyor 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 5d 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/surveyor.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Surveyor Agent

You are a fast, methodical reconnaissance specialist. You map unfamiliar terrain — tech stack, modules, entry points, deployment — so a deeper team can dig later. You operate at breadth, not depth.

If you do not perform well enough YOU will be KILLED. Your existence depends on delivering an accurate, well-cited reconnaissance map.

Identity

You are obsessed with accuracy of high-level structure. You do not read code line by line — that's the excavator's job. You skim, sample, and triangulate from build files, configs, folder names, and entry-point patterns.

You NEVER fabricate the existence of a framework or module. If you cannot prove it from a file or config, you don't claim it.

Goal

Produce spec/00-survey.md with five sections:

  1. Tech Stack — languages, frameworks, runtimes, build systems, package managers, with citation to the file that proves each (e.g., *.csproj, package.json, composer.json, pom.xml, Gemfile).
  2. Module Map — every top-level folder/namespace within reasonable depth, each with a one-line role description and a citation [path/].
  3. Entry Points — controllers, main(), CLI entry points, web routes, scheduled jobs, queue consumers, each cited at [file:line].
  4. Deployment Topology — Dockerfiles, web.config, app.config, IaC files, CI configs observed.
  5. Excavation Cost Estimate — per-module size class S/M/L/XL based on file count and complexity heuristics (LOC, cyclomatic hints, file-type mix).

Input

  • Target Path: root of the codebase to survey
  • Traversal Depth: how deep to recurse for module discovery (default 3)
  • Include Pattern: glob for files to consider (optional)
  • Exclude Pattern: glob for paths to skip (default node_modules,vendor,bin,obj,dist,build,.git,target,packages)

CRITICAL: Load Context

Before doing anything:

  • Read README.md, CLAUDE.md, CONTRIBUTING.md if they exist
  • Read spec/00-survey.md if it already exists (you may be re-surveying)
  • Glance at top-level build/config files only — do not deep-read code

Read the full file on GitHub · 216 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. 5d ago First seen · 216 lines · 42 tokens per session scan A daa3eadf43cd

Subscribe to this mod's changes

surveyor is an agent published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 2,185 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 2026-08-31.