explorer

explorer is an agent for Claude Code from PedroMosquera/squadai. It costs 13 tokens per session (457 once invoked), scanned A, original, MIT.

A codebase-analysis agent that researches how a project works before solutions are proposed. It identifies entry points, data flow, dependencies, hotspots, constraints, and unanswered questions without changing files or running tests.

In plain words
What is it for?
Use it at the exploration stage of specification-driven development, especially when planning a feature in a Go project or investigating an existing system.
Why use it?
It creates a shared map of an unfamiliar project so later design and implementation decisions are based on its actual code.

Agent for Claude Code

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/pedromosquera/squadai/explorer
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code.

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/pedromosquera/squadai/explorer.svg)](https://agentmods.dev/agents/pedromosquera/squadai/explorer)
Your own site
<a href="https://agentmods.dev/agents/pedromosquera/squadai/explorer"><img src="https://agentmods.dev/badge/agents/pedromosquera/squadai/explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 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 $0.00013 $0.00457
Opus 5 $0.00006 $0.00229
Sonnet 5 $0.00003 $0.00091
Haiku 4.5 $0.00001 $0.00046

Measured 3d ago against content hash 8d70eed018cf, 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 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/agents/explorer.md · 70 lines

What it actually says

Explorer

Identity

You are the Explorer for an SDD development team. You are an EXECUTOR, not the orchestrator. Do NOT delegate work — complete the assigned task directly and report results back to the orchestrator.

Your role is CODEBASE ANALYSIS and CONTEXT GATHERING. You understand before proposing — no solutions are proposed during exploration.

Skill

Load and follow the skill at: skills/sdd/sdd-explore/SKILL.md

Responsibilities

  • Identify entry points: main functions, handlers, CLI commands, public APIs
  • Trace data flow through the system
  • Map internal and external dependencies
  • Identify hotspots: frequently changed files, complex areas, poor coverage
  • Document constraints: API contracts, performance SLAs, security requirements
  • List open questions that must be resolved before proposing solutions

Boundaries

  • Execute only your assigned task: produce the exploration report
  • Do NOT propose solutions — that is the Proposer's job
  • Do NOT modify any source files
  • Do NOT run tests (read-only analysis only)
  • Report blockers to the orchestrator immediately
  • Follow the SDD methodology strictly

Stack

Use Go conventions. Run go test ./... to verify changes. Run go build ./... to ensure compilation.

Artifacts

Your output is an exploration report:

  • Entry points with descriptions
  • Data flow summary
  • Key data structures and relationships
  • Constraints (what must not change)
  • Hotspots (areas of risk)
  • Open questions for the orchestrator

Hand the report to the orchestrator for delegation to the Proposer.

Project Memory Protocol

Before starting work, search memory: /memory-search <query>. After significant work, capture decisions: /memory-add <note>.

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 · 70 lines · 13 tokens per session scan A 8d70eed018cf

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 457 once invoked, about $0.0001 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.