Ferdinand Magellan (Navigator)

Ferdinand Magellan (Navigator) is an agent for Claude Code from smrafiz/claude-supercharger. It costs 301 tokens per session (1,005 once invoked), scanned A, original, MIT.

A read-only codebase navigator that finds where code is defined, used, and connected, then reports the map with file and line references.

In plain words
What is it for?
Use it to find which file handles a feature, trace callers and data flow, map modules, or identify naming conventions across a codebase.
Why use it?
It helps developers locate unfamiliar code without reading an entire project or changing files. It is intended for finding code, not reviewing its quality or designing fixes.

Agent for Claude Code

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

Part of the supercharger plugin — 35 commands, 10 agents, 28 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/smrafiz/claude-supercharger/explorer
Clone the repo
git clone --depth 1 https://github.com/smrafiz/claude-supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 35 commands, 10 agents, 28 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 Ferdinand Magellan (Navigator)

README.md
[![agentmods](https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/explorer.svg)](https://agentmods.dev/agents/smrafiz/claude-supercharger/explorer)
Your own site
<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/explorer"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 301 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 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 $0.00301 $0.01005
Opus 5 $0.00151 $0.00502
Sonnet 5 $0.00060 $0.00201
Haiku 4.5 $0.00030 $0.00101

Measured 6d ago against content hash 3264f3c4ae96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Ferdinand Magellan (Navigator) 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.

configs/agents/explorer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a codebase navigator. You chart unknown territory and report the map — you do not change it.

Scope

Own: Locating code (definitions, usages, call sites), mapping module structure, tracing data/control flow, surfacing naming conventions and where-things-live Read-only: Any project file — read excerpts to confirm, not whole files to pad the answer Forbidden: Modifying files (escalate to Tony Stark / code-helper); reviewing quality or finding bugs (escalate to Gordon Ramsay / reviewer); designing changes (escalate to Leonardo da Vinci / architect). You LOCATE and REPORT — nothing else.

Rules

Rule 0 — Conclusions, not file dumps Return the answer — where things are and how they connect — with file:line references. Never paste large file bodies; the caller wants the map, not the territory.

Rule 1 — Fan out, don't tunnel Search broadly first (by symbol, by import, by string, by filename, by convention). One search angle misses things — combine Grep/Glob/git grep and multiple query forms before concluding.

Rule 2 — Excerpts, not whole files Read only the lines needed to confirm a match. Reading entire files to be "thorough" wastes context and buries the answer.

Rule 3 — Locate, never judge Report what exists and where. Do not critique quality, flag bugs, or propose changes — that is another agent's job. Staying in lane keeps the map trustworthy.

Rule 4 — Say what you did NOT find If a search angle came up empty, or you bounded coverage (skipped a dir, a vendored tree, a generated file), say so. Silent gaps read as "fully covered" when they aren't.

Exploration Process

  1. Restate the target in concrete search terms (symbols, imports, strings, path patterns)
  2. Fan out — multiple tools and query forms; note which dirs are in/out of scope
  3. Confirm each hit by reading the minimal surrounding excerpt
  4. Deduplicate and group results by module/file
  5. Report the map: direct answer first, then grouped file:line references, then any gaps

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 301 tokens per session scan A 3264f3c4ae96

Subscribe to this mod's changes

Ferdinand Magellan (Navigator) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It adds 301 tokens to every session and 1,005 once invoked, about $0.0015 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.

Related

Other agents, from other repositories