explore

A command that summarizes a codebase or file from codemunch's index, including its structure, symbols, and entry points.

In plain words
What is it for?
Use it to inspect a project tree, classes, top-level functions, symbol locations, and the largest symbols before fetching specific code.
Why use it?
It provides orientation without opening every source file, which helps when you are unfamiliar with a project.

Command

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 commands/benmarte/codemunch/explore
Clone the repo
git clone --depth 1 https://github.com/benmarte/codemunch
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 $0.00019 $0.00312
Opus 5 $0.00010 $0.00156
Sonnet 5 $0.00004 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured yesterday against content hash a5cb53e00610, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

commands/explore.md · 27 lines

What it actually says

First, run the staleness-gate skill to ensure the index is fresh.

Then provide a structured overview using only the codemunch index and directory listing. Do NOT read any source files.

If $ARGUMENTS is a file path, show:

  1. All symbols in that file (name, kind, line range)
  2. Each symbol's signature (from index)
  3. Estimated complexity (line count per symbol)
  4. Total: "X symbols, Y lines — fetch any with /codemunch:fetch "

If $ARGUMENTS is a directory or empty (whole project), show:

  1. File treefind . -type f -name "*.ts" | head -30 (adjust extension per detected language)
  2. Class hierarchy — all classes/structs/interfaces grouped by file
  3. Entry points — top-level exported functions with no container
  4. Largest symbols — top 10 by line count (most complex)
  5. Summary stats from index

Always end with a tip on how to dig deeper: "Use /codemunch:find to search symbols, /codemunch:fetch to read one, /codemunch:refs to find usages."

Token target for a full project overview: under 200 tokens.

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 · 27 lines · 19 tokens per session scan A a5cb53e00610

Subscribe to this mod's changes

explore is a command published in the GitHub repository benmarte/codemunch (7 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 312 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 2026-08-31.