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.
npx agentmods add commands/geckse/markdown-vdb/doctorgit clone --depth 1 https://github.com/geckse/markdown-vdbWrote 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/commands/geckse/markdown-vdb/doctor)<a href="https://agentmods.dev/commands/geckse/markdown-vdb/doctor"><img src="https://agentmods.dev/badge/commands/geckse/markdown-vdb/doctor.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 | $0.00015 | $0.01843 |
| Opus 5 | $0.00008 | $0.00922 |
| Sonnet 5 | $0.00003 | $0.00369 |
| Haiku 4.5 | $0.00002 | $0.00184 |
Grade A, and why
doctor 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 4d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb doctor
Run a read-only health check for the current project. doctor reports configuration discovery,
embedding connectivity, index integrity, source discovery, frontmatter Relations, and Shard/Topic
configuration in one result.
Usage
mdvdb doctor [OPTIONS]
Options
This command has no command-specific options. It accepts the global options,
including --root, --json, --verbose, and --no-color.
Diagnostic checks
A successful diagnostic run returns nine checks in this order:
| # | Check | What it validates |
|---|---|---|
| 1 | Config loaded | Shows the resolved embedding provider, model, and dimensions. The command has already loaded configuration when this check is emitted. |
| 2 | User config | Looks for ~/.mdvdb/config.yaml, or config.yaml below MDVDB_CONFIG_HOME. A missing user config is a warning because it is optional. |
| 3 | Project config | Checks that the project has a .markdownvdb/ directory. |
| 4 | API key | Explicitly validates OPENAI_API_KEY for the OpenAI provider. Mock needs no key; other providers are reported as configured and are actually exercised by the connectivity check. |
| 5 | Provider reachable | Sends one test embedding request with a five-second timeout. Authentication, endpoint, model, and network failures surface here. |
| 6 | Index | Reports documents, chunks, edge vectors, and vectors. A healthy index has vectors = chunks + edges. An empty or mismatched index warns. |
| 7 | Source directories | Discovers Markdown in the configured source directories and reports the file count. |
| 8 | Relations | Warns about dangling frontmatter Relation targets, schema target folders with no indexed files, and unquoted [[wikilink]] values that YAML parsed as nested lists. |
| 9 | Shards | Validates Shard definitions, target folders, and local Topic definitions. Missing or malformed configuration warns. |
Each check is Pass, Warn, or Fail. Warnings describe repairable or optional conditions; failures
normally prevent an operation such as source discovery or provider access from working.
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.
- 4d ago First seen · 185 lines · 15 tokens per session scan A d0974fb35ca8
doctor is a command published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 20d ago), licensed MIT. It adds 15 tokens to every session and 1,843 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 2026-08-30.
Other commands, from other repositories
refactor-function
Automated function complexity reduction using multi-agent workflow.
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
issue-amend
Re-snapshot the active issue's scope from the spec, clear verified and reviewed receipts, and record the change as a permanent amendment.
quick-fix
Fast-track workflow for small bug fixes.
sync-linear
Sync current work with Linear ticket status.