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.
git clone --depth 1 https://github.com/nicholasglazer/gnosis-mcpWrote 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.
[](https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/doc-explorer)<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>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.
| Model | Per session | Once 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 |
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.
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)
- 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. - Read the top 2-3 hits via
mcp__gnosis__get_doc(path=...). - Traverse with
mcp__gnosis__get_related(path=..., depth=2, include_titles=True)to find connected docs. Filter byrelation_typeif you need to cut noise:relates_to— curated frontmatter links (highest signal)content_link— markdown[text](path.md)linksgit_co_change— files edited together in commits
- Cross-reference against actual code with
Read,Glob,Grep. Docs drift; never trust them blindly when something in the code could contradict them. - History via
mcp__gnosis__search_git_history(query, since="6m")when the user asks "why". - Macro view via
mcp__gnosis__get_graph_stats()ormcp__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) orcorpus-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:linecitation. - 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.
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.
- 7d ago First seen · 91 lines · 42 tokens per session scan A 27d5a8b5c51f
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.
Other agents, from other repositories
file-analyzer
Reads a batch of source files and produces FileSummary objects (summary, exports, relationships, tags) for vault-anything's raw layer.
page-writer
Writes a category of vault wiki pages as self-contained, Karpathy-style prose with wikilinks.
doc-generator
Documentation generation subagent.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.