explorer CLAUDE.md

explorer CLAUDE.md is an instructions file for coding agents from anantadwi13/explorer. It costs 2,428 tokens per session, scanned A, original, MIT.

Project instructions for Explorer, a single-file-directory browser built with Go and a React web interface that previews text, Markdown, and images over HTTP.

In plain words
What is it for?
Use them to build, test, run, lint, package, or develop Explorer locally and in Docker.
Why use it?
They clarify the correct build and test commands, including the required web build before the Go binary can serve the interface.

Instructions file

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 instructions/anantadwi13/explorer/claude-md
Clone the repo
git clone --depth 1 https://github.com/anantadwi13/explorer

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anantadwi13/explorer/claude-md.svg)](https://agentmods.dev/instructions/anantadwi13/explorer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/anantadwi13/explorer/claude-md"><img src="https://agentmods.dev/badge/instructions/anantadwi13/explorer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,428 This file is loaded in full into every session.
When invoked 2,428 The same file — it is already loaded in full.
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 $0.02428 $0.02428
Opus 5 $0.01214 $0.01214
Sonnet 5 $0.00486 $0.00486
Haiku 4.5 $0.00243 $0.00243

Measured 3d ago against content hash beebf971ec69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explorer CLAUDE.md 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 3d 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.

CLAUDE.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

explorer is a single-binary local directory browser: a Go HTTP server with an embedded React+Vite SPA. Point it at a directory; it serves a read-only browser over HTTP with markdown/text/image preview and deep-linkable URLs.

Commands

make build          # full build: web SPA → embed → Go binary (./explorer)
make web            # SPA only (cd web && npm ci && npm run build)
make test           # go test ./cmd/... ./internal/... (excludes web/)
make dev-server     # build + run Go binary against ./testdata
make dev-web        # Vite dev server on :5173, proxies /api /raw /assets to :8080
make run            # full build then run against ./testdata
make clean          # remove ./explorer and internal/server/ui/dist
make docker         # build explorer:latest

# Single Go test
go test ./internal/server -run TestFileMarkdown -v

# SPA lint (no Go linter configured)
cd web && npm run lint

make build is required (not go build alone) — the Go binary uses //go:embed all:dist and serves an HTTP 404 fallback (the stock http.ServeFileFS response when dist/index.html is missing) if internal/server/ui/dist/ is empty.

The dev workflow is two-process: make dev-server (Go on :8080) + make dev-web (Vite on :5173). Vite proxies API/raw paths to the Go server.

Architecture

Single-binary embed

The React SPA builds to internal/server/ui/dist/ (configured in web/vite.config.ts via outDir: '../internal/server/ui/dist'). internal/server/ui/ui.go does //go:embed all:dist to bake it into the Go binary. The static handler (internal/server/static.go) serves exact file matches and falls back to index.html for SPA client-routes.

internal/server/ui/dist/ is committed to source control so module-proxy installs (go install / go run github.com/anantadwi13/explorer/cmd/explorer@latest) produce a working binary without Node. Any change under web/src/ requires running make web-commit (or make web + git add internal/server/ui/dist) in the same commit so the embedded SPA stays in sync with the source.

Read the full file on GitHub · 90 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. 3d ago First seen · 90 lines · 2,428 tokens per session scan A beebf971ec69

Subscribe to this mod's changes

explorer CLAUDE.md is an instructions file published in the GitHub repository anantadwi13/explorer (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,428 tokens to every session, about $0.0121 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.