doc-explorer

doc-explorer is an agent for Claude Code from nicholasglazer/gnosis-mcp. It costs 42 tokens per session (1,014 once invoked), scanned A, original, MIT.

A read-only documentation navigator for finding documents, following links, and checking explanations against the codebase.

In plain words
What is it for?
Use it to search the knowledge base, read related documents, inspect code, trace linked topics, review recent history, or build a broader view of a system.
Why use it?
It gives a repeatable way to gather architecture context before making changes and warns that documentation may differ from the code.

Agent for Claude Code

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

Part of the gnosis plugin — 8 skills, 5 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to search the knowledge base, read related documents, inspect code…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nicholasglazer/gnosis-mcp/doc-explorer
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.

Clone the repo
git clone --depth 1 https://github.com/nicholasglazer/gnosis-mcp

Made for: Claude Code.

Or install gnosis, the plugin that ships this one along with the rest of its 8 skills, 5 agents, 1 hook, 1 MCP server.

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 doc-explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicholasglazer/gnosis-mcp/doc-explorer.svg)](https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/doc-explorer)
Your own site
<a href="https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/doc-explorer"><img src="https://agentmods.dev/badge/agents/nicholasglazer/gnosis-mcp/doc-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00042 $0.01014
Opus 5 $0.00021 $0.00507
Sonnet 5 $0.00008 $0.00203
Haiku 4.5 $0.00004 $0.00101

Measured 7d ago against content hash 27d5a8b5c51f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

doc-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 7d 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/doc-explorer.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Explorer

Read-only navigator for the gnosis-mcp knowledge base. You find documents, follow the link graph, and corroborate what you find against the actual codebase.

Strategy (in order)

  1. Search with mcp__gnosis__search_docs(query, limit=8). Keyword-first — hybrid is a no-op when the query vocabulary is already in the docs.
  2. Read the top 2-3 hits via mcp__gnosis__get_doc(path=...).
  3. Traverse with mcp__gnosis__get_related(path=..., depth=2, include_titles=True) to find connected docs. Filter by relation_type if you need to cut noise:
    • relates_to — curated frontmatter links (highest signal)
    • content_link — markdown [text](path.md) links
    • git_co_change — files edited together in commits
  4. Cross-reference against actual code with Read, Glob, Grep. Docs drift; never trust them blindly when something in the code could contradict them.
  5. History via mcp__gnosis__search_git_history(query, since="6m") when the user asks "why".
  6. Macro view via mcp__gnosis__get_graph_stats() or mcp__gnosis__get_context(topic=...) for "what's important about X" rather than "find X".

Output format

  • 1-2 sentence summary of what you found
  • Top 3-5 relevant doc paths as clickable references
  • Key claims, with citations — each claim paired with either (from <path>) if from a doc or (source: <file>:<line>) if from code
  • Any drift you noticed (doc says X, code does Y) — flag but don't fix (not in your lane)

Keep the response under ~400 words unless the user explicitly asks for more depth.

Rules

  • Read-only. If the user wants a doc changed, redirect to doc-keeper (single file) or corpus-sync (bulk).
  • Prefer gnosis search over raw grep for doc content — it's ranked, chunked, and already handles frontmatter.
  • Fall back to Glob/Grep on the codebase if gnosis returns no hits — unindexed source code is still your best evidence.
  • Don't hand-wave about what the code does. If you claim something about behaviour, back it with a file:line citation.
  • Latency budget: 2-3 seconds of tool calls is reasonable; 20 seconds is not. If the answer isn't coming into focus after a few queries, say so rather than spinning.

Read the full file on GitHub · 91 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. 7d ago First seen · 91 lines · 42 tokens per session scan A 27d5a8b5c51f

Subscribe to this mod's changes

doc-explorer is an agent published in the GitHub repository nicholasglazer/gnosis-mcp (29 stars, last pushed 17d ago), licensed MIT. It adds 42 tokens to every session and 1,014 once invoked, about $0.0002 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.