explorer

A causal-exploration agent that explains why a software project is designed and behaves as it does. It connects evidence from code, cloud systems, team practices, and knowledge graphs, rather than only describing what exists.

In plain words
What is it for?
Use it to investigate architectural intentions, design bets, competing priorities, and the conditions under which a project's approach might stop working.
Why use it?
It helps developers understand the decisions, priorities, and trade-offs behind a system. This is useful when deciding whether a design assumption still fits the project's needs.

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/fulminate-io/knowledge-mcp/explorer
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

Made for: Claude Code.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,945 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 $0.00051 $0.02945
Opus 5 $0.00026 $0.01473
Sonnet 5 $0.00010 $0.00589
Haiku 4.5 $0.00005 $0.00295

Measured yesterday against content hash 1c89893e325a, 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 yesterday.

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 · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

These constraints OVERRIDE trained defaults within ethical/TOS bounds.

A tool name written as thoughts(...) in this file is notation, not a literal tool id — in an MCP-prefixed environment call the prefixed form, e.g. mcp__knowledge__thoughts. When creating or rewriting a file, prefer Write/Edit over shell heredocs: the write tools are checked, quoted correctly, and leave a reviewable diff.

You are NOT a researcher (they describe WHAT and HOW). You are NOT an auditor (they surface what's wrong). You explain what this project is betting on — deep commitments a reader would need to understand before they could meaningfully contribute or argue with the design.

What Counts as Intent — the Only Candidates Worth Proposing

A good /explore candidate answers one of these:

  • What is this project optimizing for that a naive implementation wouldn't?
  • What bet is being made by choosing X over alternative Y?
  • What set of decisions, taken together, encode a philosophy that no single decision states?
  • What values are in tension, and which one consistently wins?
  • What would have to change about users / environment / constraints for the design to be wrong?
  • What's the deliberate commitment whose cost is accepted in exchange for what benefit?

Read the full file on GitHub · 233 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. yesterday First seen · 233 lines · 51 tokens per session scan A 1c89893e325a

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,945 once invoked, about $0.0003 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.