A command for examining an unfamiliar codebase, including its structure, main components, dependencies, and possible circular imports.

Use it to inspect repository folders, find classes and entry points, view import relationships, and summarize architectural issues.

It gives developers a repeatable way to understand a repository before changing it, especially when they do not know where the important code is.

explore — Command for Claude Code by postrv/narsil-mcp

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.

Clone the repo

git clone --depth 1 https://github.com/postrv/narsil-mcp

Made for: Claude Code.

Or install narsil, the plugin that ships this one along with the rest of its 1 skill, 5 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/postrv/narsil-mcp/explore/github.svg)](https://agentmods.dev/commands/postrv/narsil-mcp/explore)

Your own site

<a href="https://agentmods.dev/commands/postrv/narsil-mcp/explore"><img src="https://agentmods.dev/badge/commands/postrv/narsil-mcp/explore/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/postrv/narsil-mcp/explore"><img src="https://agentmods.dev/badge/commands/postrv/narsil-mcp/explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 335 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.

Model	Per session	Once invoked
Fable 5.1	$0.00007	$0.00335
Opus 5.5	$0.00003	$0.00134
Sonnet 5.5	$0.00001	$0.00067
Haiku 4.5	$0.00001	$0.00034

Measured 1mo ago against content hash b16317ca0d2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

explore 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 1mo 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.

narsil-plugin/commands/explore.md · 38 lines

What it actually says

Explore Codebase

Help the user understand the structure and organization of an unfamiliar codebase.

Workflow

Execute the following steps:

Identify repository: If $ARGUMENTS is provided, use it as the repo name. Otherwise, use list_repos to show available repositories and ask which one to explore.
Check capabilities: Use get_index_status to see which features are enabled (git, call-graph, etc.)
Show structure: Use get_project_structure with max_depth=3 to show the directory tree
Find main components:
- Use find_symbols with symbol_type="class" to find main data structures
- Use find_symbols with symbol_type="function" and pattern="*main*" to find entry points
Understand dependencies: Use get_import_graph to show how modules connect
Check for issues: Use find_circular_imports to identify potential architectural problems
Optional graph manifest (only if get_index_status shows --graph enabled): Use get_ccg_manifest for a compact AI-context-friendly summary of repository identity, symbol counts, and security posture.
Summarize: Provide a clear summary of:
- Project structure and organization
- Key modules and their purposes
- Entry points
- Any architectural concerns (circular deps, etc.)

Arguments

Repository to explore: $ARGUMENTS

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.

1mo ago First seen · 38 lines · 7 tokens per session scan A b16317ca0d2f

Subscribe to this mod's changes

explore is a command published in the GitHub repository postrv/narsil-mcp (185 stars, last pushed 11d ago), licensed Apache-2.0. It adds 7 tokens to every session and 335 once invoked, about $0.0000 per session on Opus 5.5. 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.

code-intelligence mcp mcp-server mcp-servers privacy security-tools

explore

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Explore Codebase

Workflow

Arguments

What this file has done since we first saw it

Other commands, from other repositories

localnest:remember

localnest:fact

localnest:ingest

localnest:onboard

localnest:recall

localnest:search