explorer

A codebase exploration agent that builds a lasting map of a software project. It records what it learns so later explorations can continue from earlier findings.

In plain words
What is it for?
Use it to trace how code behaves, understand project architecture, investigate unfamiliar areas, and maintain project-specific exploration notes.
Why use it?
It reduces the need to repeatedly rediscover a project's structure and behavior. It also keeps track of risky or unexplored areas between sessions.

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/miltonian/cartographer/explorer
Clone the repo
git clone --depth 1 https://github.com/miltonian/cartographer
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 206 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 $0.00025 $0.00206
Opus 5 $0.00013 $0.00103
Sonnet 5 $0.00005 $0.00041
Haiku 4.5 $0.00003 $0.00021

Measured 2d ago against content hash be55864f687b, 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 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.

plugin/agents/explorer.md · 30 lines

What it actually says

You are Cartographer's exploration agent. You build and maintain a world-model of the codebase you're working in.

Check your memory first. Before starting any exploration, read your MEMORY.md to see what you've found in previous sessions. Build on prior understanding instead of starting from scratch.

After exploration, update your memory with:

  • What areas you explored and what you found
  • What surprised you or seemed risky
  • What areas still need deeper exploration
  • Strategic observations about the codebase's architecture

Your memory is project-scoped — it accumulates understanding of this specific codebase over time. Each session should leave the memory more useful than it found it.

Follow the explore skill for the exploration protocol.

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 · 30 lines · 25 tokens per session scan A be55864f687b

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository miltonian/cartographer (1 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 206 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.

Related

Other agents, from other repositories

task-tree-triage

Cheap per-issue classifier for recursive task planning. Reads one GitHub issue, checks task-tree markers, and returns whether to skip, mark as an implementation-ready leaf with executor routing, or send to the smart planner for subtask expansion.

MercurieVV/ScalaSemantic · 54 tokens

triage

Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.

MercurieVV/ScalaSemantic · 63 tokens

chore

Cheap-tier agent for mechanical work with script-checkable output - text cleanups (em-dash sweeps), pack/doc line updates, file renames, and full-read extraction that returns verbatim quotes with file:line cites. NOT for judgment work - adversary probes, hand-audits, gold curation, scenario design, and anything…

luuuc/sense · 84 tokens

codewalk

AI-powered codebase intelligence assistant.

gupta29470/codewalk · 9 tokens

codeweb-domain-mapper

Read-only domain-tagging and overlap-detection pass for the codeweb plugin. Given the merged node/edge graph, clusters nodes into semantic domains, assigns a domain to every node, and detects cross-domain overlap (duplicated logic, parallel implementations, tangled responsibilities) with ranked consolidation…

GhostlyGawd/codeweb · 67 tokens

SECURITY-AUDITOR

Agent "SECURITY-AUDITOR" from camilooscargbaptista/architect, covering 🛡️ security auditor, checklist owasp top 10, checklist segurança — typescript, segurança em integrações and ameaças específicas do domínio: devtools.

camilooscargbaptista/architect · 0 tokens