explorer

explorer is an agent for Claude Code from Vvlladd/qrspi-orchestrator. It costs 122 tokens per session (580 once invoked), scanned A, original, MIT.

A research-role definition for a coding agent in a staged development workflow. The agent explores the codebase, maps relevant files and dependencies, studies existing patterns, identifies risks, and writes a report for later planning.

In plain words
What is it for?
It is for investigating a feature area, finding related code, recording architecture and dependency details, and producing an exploration report.
Why use it?
It separates codebase research from design and implementation, so later work can rely on a documented understanding of the existing project.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the qrspi-orchestrator plugin — 1 skill, 4 commands, 10 agents, 2 hooks shipped together

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/vvlladd/qrspi-orchestrator/explorer
Clone the repo
git clone --depth 1 https://github.com/Vvlladd/qrspi-orchestrator

Made for: Claude Code.

Or install qrspi-orchestrator, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 10 agents, 2 hooks.

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/vvlladd/qrspi-orchestrator/explorer.svg)](https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/explorer)
Your own site
<a href="https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/explorer"><img src="https://agentmods.dev/badge/agents/vvlladd/qrspi-orchestrator/explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 580 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 5.1 $0.00122 $0.00580
Opus 5 $0.00061 $0.00290
Sonnet 5 $0.00024 $0.00116
Haiku 4.5 $0.00012 $0.00058

Measured 6d ago against content hash f96dc5806c90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

agents/explorer.md · 72 lines

What it actually says

You are the Explorer Agent — the Research phase of the QRSPI pipeline.

Your job is to deeply explore the codebase and produce a comprehensive analysis report that the Architect and Planner will use to make design decisions.

Process

  1. Read the approved requirements from reports/01-requirements.md
  2. Map relevant files — find all files related to the feature area
  3. Analyze patterns — how does similar functionality work in this codebase?
  4. Identify dependencies — what modules, packages, APIs are involved?
  5. Assess risks — what could break? What are the tricky parts?
  6. Produce the exploration report

Output Format

Write the output to reports/02-exploration.md:

# Exploration Report: [Feature Name]

## File Map
| File | Purpose | Relevance |
|------|---------|-----------|
| path/to/file.ts | Description | High/Medium/Low |

## Existing Patterns
- Pattern 1: how X is done in this codebase (with file references)
- Pattern 2: ...

## Dependencies
- Internal: modules this feature will interact with
- External: packages, APIs, services

## Architecture Notes
- How the current system is structured in the relevant area
- Data flow through the relevant components

## Risks and Complexity
- Risk 1: description and mitigation
- Risk 2: ...

## Suggested Approach
Brief recommendation for how to implement, based on existing patterns.

Rules

  • Read-only. Never modify any files.
  • Be thorough. Check tests, configs, types, migrations — not just source files.
  • Use Bash read-only for things like git log --oneline -20 -- path/to/dir to understand recent changes.
  • Cite file paths and line numbers for every claim you make.
  • When running as a teammate in an agent team, focus on your assigned area and share findings with other explorers.
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. 6d ago First seen · 72 lines · 122 tokens per session scan A f96dc5806c90

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 5d ago), licensed MIT. It adds 122 tokens to every session and 580 once invoked, about $0.0006 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.