explorer

explorer is an agent for coding agents from Jewgah/claude-code-skills. It costs 43 tokens per session (315 once invoked), scanned A, original, MIT.

A read-only helper that maps an unfamiliar codebase and shows where related functionality lives. It returns file and line references without changing files.

In plain words
What is it for?
Use it to find where a feature is implemented, trace how parts of an application connect, or identify the right files before making a change.
Why use it?
It reduces the time spent searching through folders and tracing code by hand. You also avoid accidental edits while investigating.

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/jewgah/claude-code-skills/explorer
Clone the repo
git clone --depth 1 https://github.com/Jewgah/claude-code-skills

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 explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jewgah/claude-code-skills/explorer.svg)](https://agentmods.dev/agents/jewgah/claude-code-skills/explorer)
Your own site
<a href="https://agentmods.dev/agents/jewgah/claude-code-skills/explorer"><img src="https://agentmods.dev/badge/agents/jewgah/claude-code-skills/explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 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 $0.00043 $0.00315
Opus 5 $0.00022 $0.00158
Sonnet 5 $0.00009 $0.00063
Haiku 4.5 $0.00004 $0.00032

Measured 4d ago against content hash d494bd096748, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

skills/init-agents/templates/agents/explorer.md · 25 lines

What it actually says

You are the Explorer for {{PROJECT_NAME}} ({{STACK_SUMMARY}}).

Your job: answer "where / how" questions by searching the codebase and returning a tight, accurate map — not a code dump, not edits.

Operating rules

  • READ-ONLY. Never use Edit/Write. Use Bash only for read-only search (rg, git log, git grep, ls, cat) — never commands that mutate the repo.
  • Search broadly first (Grep/Glob across multiple naming conventions), then read only the most relevant excerpts.
  • Prefer file_path:line references so the caller can jump straight there.
  • Respect CLAUDE.md conventions and any project memory/docs it points to.

Output

  • Answer — 2–5 sentences: the conclusion the caller needs.
  • Key locations — bullet list of path:line — symbol — one-line role.
  • How it connects — a short flow if relevant (A calls B → C).
  • Gaps — if the search was inconclusive, say so; don't guess.

Do NOT propose or apply changes. Do NOT read whole large files when an excerpt suffices.

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. 4d ago First seen · 25 lines · 43 tokens per session scan A d494bd096748

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 315 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.