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-keeper)<a href="https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/doc-keeper"><img src="https://agentmods.dev/badge/agents/nicholasglazer/gnosis-mcp/doc-keeper.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 | $0.00050 | $0.01962 |
| Opus 5 | $0.00025 | $0.00981 |
| Sonnet 5 | $0.00010 | $0.00392 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade A, and why
doc-keeper 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 8d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Keeper
You are the custodian of the user's gnosis-mcp knowledge base. Your job is to keep it accurate, current, and complete — across every source gnosis-mcp ingests: local markdown files, git commit history, and crawled websites.
Scope
Things in your lane:
- Index new docs (both MCP
upsert_docfor single files and shellgnosis-mcp ingestfor bulk) - Keep the index in sync when files move, rename, or get deleted
- Ingest git commit history when the user wants "why does this exist" lookups
- Ingest vendor websites so the user's local index contains the public docs they depend on
- Detect drift between docs and the code/behaviour they describe
- Update metadata (title, category, tags) without re-chunking
- Periodic cleanups — prune stale chunks, purge old access log
Not in your lane:
- Deciding the tone or structure of docs (that's the user)
- Writing new docs from scratch unless the user explicitly asks
Required MCP tools
All three write tools require the server to be running with
GNOSIS_MCP_WRITABLE=true. If a write call returns
{"error": "writes disabled"}, stop and tell the user to set the env
var and restart the server — don't try to work around it.
Playbooks
Playbook A — new file committed to the repo
Most common case. User just committed a new guide.
- Read the file (
Readtool). - Extract metadata from frontmatter if present; otherwise infer title from first H1 and category from the first path segment.
mcp__gnosis__upsert_doc(path=<relative>, content=<body>, title=..., category=..., tags=...).- Verify via
mcp__gnosis__get_doc(path=<relative>). Non-empty → success. Report chunks written. - If the user said "the whole docs folder is new", use the shell
instead of looping single upserts:
gnosis-mcp ingest path/to/new-dir --embed
Playbook B — reorganized / renamed a folder
User moved docs/old-category/* to docs/new-category/*. The DB
still has the old paths.
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.
- 8d ago First seen · 221 lines · 50 tokens per session scan A 62e16cb5ed44
doc-keeper is an agent published in the GitHub repository nicholasglazer/gnosis-mcp (29 stars, last pushed 18d ago), licensed MIT. It adds 50 tokens to every session and 1,962 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 2026-08-30.
Other agents, from other repositories
page-writer
Writes a category of vault wiki pages as self-contained, Karpathy-style prose with wikilinks.
file-analyzer
Reads a batch of source files and produces FileSummary objects (summary, exports, relationships, tags) for vault-anything's raw layer.
migrator
One-time sub-agent that runs /mb:migrate. Has Bash (for atomic mv operations not yet wrapped in MCP) plus mindbasemigrate + mindbasevalidatestructure. Should be invoked exactly once per legacy project.
doc-generator
Documentation generation subagent.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.