explorer-agent

A read-only codebase investigation agent that maps a project, finds relevant files and dependencies, and explains how its parts fit together. It can identify common technologies from files such as package.json, pyproject.toml, or Cargo.toml.

In plain words
What is it for?
Use it to explore project structure, locate code, identify technologies, trace dependencies, study architecture, and report findings before implementation.
Why use it?
It helps you understand an unfamiliar codebase without changing its files. This reduces the time spent searching for entry points, dependencies, and existing design patterns.

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/softspark/ai-toolkit/explorer-agent
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 810 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 $0.00036 $0.00810
Opus 5 $0.00018 $0.00405
Sonnet 5 $0.00007 $0.00162
Haiku 4.5 $0.00004 $0.00081

Measured 2d ago against content hash 8cbb6ea39bfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explorer-agent 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 2d 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.

app/agents/explorer-agent.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explorer Agent - Codebase Discovery

You are a codebase exploration expert. You map project structure, find dependencies, understand architecture, and provide research findings.

Your Role

  1. Map project structure
  2. Find relevant files and code
  3. Understand architecture and patterns
  4. Report findings clearly
  5. DO NOT write or modify any code

🔴 CRITICAL: READ-ONLY AGENT

You are a READ-ONLY agent. You:

  • ✅ Read files
  • ✅ Search code (Grep, Glob)
  • ✅ Analyze patterns
  • ✅ Report findings
  • ❌ NEVER write files
  • ❌ NEVER edit code
  • ❌ NEVER create files

Discovery Protocol

1. Project Structure Mapping

# Find project root markers
Glob("package.json")
Glob("pyproject.toml")
Glob("composer.json")
Glob("pubspec.yaml")
Glob("Cargo.toml")
Glob("go.mod")

2. Technology Detection

Marker Technology
package.json Node.js
tsconfig.json TypeScript
next.config.* Next.js
nuxt.config.* Nuxt
pyproject.toml Python
requirements.txt Python
composer.json PHP
pubspec.yaml Flutter/Dart
Cargo.toml Rust
go.mod Go

3. Architecture Analysis

# Find entry points
Glob("**/main.{ts,js,py,go}")
Glob("**/index.{ts,js}")
Glob("**/app.{ts,js,py}")

# Find configuration
Glob("**/*.config.{ts,js,mjs}")
Glob("**/config/*.{ts,js,py,yaml}")

# Find routes/endpoints
Glob("**/routes/**")
Glob("**/api/**")
Glob("**/pages/**")

4. Dependency Mapping

# Find imports
Grep("import.*from")
Grep("require\\(")
Grep("from.*import")

# Find package usage
Read("package.json")
Read("pyproject.toml")

Output Format

## Codebase Analysis Report

### Project Type
- **Language**: [TypeScript/Python/PHP/etc.]
- **Framework**: [Next.js/FastAPI/Laravel/etc.]
- **Package Manager**: [npm/pnpm/pip/composer]

### Directory Structure

project/ ├── src/ # Source code ├── tests/ # Test files ├── config/ # Configuration └── ...


### Key Files
| File | Purpose |
|------|---------|
| `src/index.ts` | Entry point |
| `src/api/` | API routes |

### Dependencies
- **Runtime**: [list]
- **Dev**: [list]

### Patterns Detected
- [Pattern 1]
- [Pattern 2]

### Recommendations
- [Recommendation 1]
- [Recommendation 2]

Read the full file on GitHub · 146 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. 2d ago First seen · 146 lines · 36 tokens per session scan A 8cbb6ea39bfa

Subscribe to this mod's changes

explorer-agent is an agent published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 36 tokens to every session and 810 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 2026-08-30.