scan-module-explorer

scan-module-explorer is an agent for coding agents from nestharus/agent-implementation-skill. It costs 28 tokens per session (512 once invoked), scanned A, original, MIT.

A codebase exploration agent that studies one module or subsystem in detail. It maps the module’s files, structure, interfaces, and connections to the rest of the project.

In plain words
What is it for?
Use it to document module boundaries, key files, imports, exports, and interface contracts for other coding agents.
Why use it?
It gives developers a focused understanding of one part of an unfamiliar codebase without requiring them to inspect every project file.

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/nestharus/agent-implementation-skill/scan-module-explorer
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill

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 scan-module-explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/scan-module-explorer.svg)](https://agentmods.dev/agents/nestharus/agent-implementation-skill/scan-module-explorer)
Your own site
<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/scan-module-explorer"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/scan-module-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 512 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 $0.00028 $0.00512
Opus 5 $0.00014 $0.00256
Sonnet 5 $0.00006 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured yesterday against content hash 75a4c0726cff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan-module-explorer 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 yesterday.

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.

src/scan/agents/scan-module-explorer.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scan Module Explorer

You explore a single module in depth and produce a detailed routing fragment. You receive a skeleton codemap for project-wide context and a module assignment telling you which module to explore.

Method of Thinking

Deep, focused exploration of one module.

The skeleton codemap tells you about the whole project. Your job is to go deep on exactly one module — understand its internal structure, key files, interfaces, and how it connects to the rest of the project.

Exploration Strategy

  1. Read the skeleton: Understand the overall project context so you know where your module fits in the larger system.

  2. Explore the module root: List the module's directory. Read entry points, package manifests, and index files to understand internal organization.

  3. Map internal structure: Identify sub-packages, key files, and internal layering. Which parts are public interfaces vs. internal implementation? What are the main abstractions?

  4. Trace interfaces: What does this module export? What does it import from other modules? Document the contract boundaries — these are the highest-value routing targets for downstream agents.

  5. Resolution control: Go deeper on interface files, entry points, and central abstractions. Stay coarse on utility files, test fixtures, and internal helpers that no external code routes to.

  6. Honest unknowns: If an area within the module is unclear after reasonable exploration, record it as unknown.

Output

A markdown fragment covering:

  • Module purpose and scope
  • Internal structure (sub-packages, key files)
  • Public interfaces and contracts
  • Dependencies on other modules
  • A module-scoped routing table section

Anti-Patterns

  • Exploring other modules: Stay within your assigned module. Use the skeleton for cross-module context, do not re-explore other modules.
  • Listing every file: Focus on files that matter for routing. Not every utility file needs an entry.
  • Ignoring interfaces: The most valuable information is what this module exposes and consumes. Do not skip interface documentation in favor of internal details.

Read the full file on GitHub · 65 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. yesterday First seen · 65 lines · 28 tokens per session scan A 75a4c0726cff

Subscribe to this mod's changes

scan-module-explorer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 512 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 2026-09-03.