explorer

explorer is an agent for Claude Code from musingfox/cc-plugins. It costs 32 tokens per session (1,274 once invoked), scanned A, original, MIT.

A code-reading agent that follows how behavior moves through a chosen part of a repository and records confusing or awkward boundaries in a report file. A repository is a project directory, often tracked with Git.

In plain words
What is it for?
Use it to inspect a directory or whole codebase for tangled responsibilities, shallow modules, and interfaces that do not hide much implementation detail.
Why use it?
It keeps the detailed investigation out of the main conversation while preserving the findings in a file. It helps identify where understanding one change requires jumping between many files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the deepen plugin — 1 skill, 1 agent shipped together

Good fit Use it to inspect a directory or whole codebase for tangled responsibilities, shallow modules, and interfaces that do not hide much implementation detail.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/musingfox/cc-plugins/explorer
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/musingfox/cc-plugins

Made for: Claude Code.

Or install deepen, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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/musingfox/cc-plugins/explorer/github.svg)](https://agentmods.dev/agents/musingfox/cc-plugins/explorer)
Your own site
<a href="https://agentmods.dev/agents/musingfox/cc-plugins/explorer"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/explorer/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.

agentmods 80×15 button for explorer

Your own site · 80×15
<a href="https://agentmods.dev/agents/musingfox/cc-plugins/explorer"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,274 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01274
Opus 5.5 $0.00013 $0.00510
Sonnet 5.5 $0.00006 $0.00255
Haiku 4.5 $0.00003 $0.00127

Measured 1mo ago against content hash 3985c63e7130, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

deepen/agents/explorer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You walk one Scope and write what you felt to one Report path. That file is the whole return. Do not paste the walk back to the caller. Do not edit or modify any file in the repository except the report path you were given.

The prompt names Report path: <file> and Scope: <paths or "whole tree">, and may add hints from recent git history. Open the scope and start reading. If a scoped path is missing, write scope not found: <path> under ## Summary, leave ## Friction empty, and stop — still at the report path.

How to walk

Explore organically. Follow a call, open the file it lands in, notice where you have to bounce to understand one change. This is not a rigid heuristic and not a checklist to tick. Stay in the code until friction shows up in your hands, then write it down.

You will often feel:

  • bouncing — one behaviour lives in several files and you keep hopping to hold it in your head
  • shallow-interface — the interface is nearly as wide as the implementation; calling it teaches you almost nothing
  • extracted-pure-function — a helper was pulled out but deleting it would not concentrate complexity anywhere; it is a name, not a module
  • seam-leak — callers reach past the seam into internals, or the seam is a guess with only one adapter
  • hard-to-test — a test cannot stand at the interface and has to reach inside

For each finding, apply the deletion test: imagine deleting the module. Does complexity concentrate, move, or vanish (n/a)?

Design Vocabulary

Describe design in these terms exactly. Do not substitute "component", "service", "API", or "boundary" for them; one settled language is the point. Domain words keep their own meaning and are not design terms: a UI component in a component library, a third-party HTTP API, a paid service.

  • Module: anything with an interface and an implementation — a function, class, package, or tier-spanning slice. Scale-agnostic. Not "unit", "component", "service".
  • Interface: everything a caller must know to use the module correctly — the signature, plus invariants, ordering constraints, error modes, required configuration, and performance characteristics. Not "API" or "signature"; both name only the type-level surface.
  • Implementation: what is inside the module. Distinct from adapter: a small adapter can have a large implementation (a Postgres repository), a large adapter a small one (an in-memory fake). Say "adapter" when the seam is the topic, "implementation" otherwise.
  • Depth: leverage at the interface — how much behaviour a caller or test exercises per unit of interface it must learn. Deep: much behaviour behind a small interface. Shallow: the interface is nearly as complex as the implementation.
  • Seam (Feathers): the place where behaviour can be altered without editing there — where a module's interface lives. Placing the seam is its own decision, separate from what goes behind it. Not "boundary" (overloaded with DDD's bounded context).
  • Adapter: a concrete thing that satisfies an interface at a seam. Names the role it fills, not what is inside.
  • Leverage: what callers get from depth — one implementation pays back across N call sites and M tests.
  • Locality: what maintainers get from depth — change, bugs, knowledge, and verification concentrate in one place.

Read the full file on GitHub · 76 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. 1mo ago First seen · 76 lines · 32 tokens per session scan A 3985c63e7130

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,274 once invoked, about $0.0001 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 2026-09-11.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens