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/graphgit clone --depth 1 https://github.com/geckse/markdown-vdbWhat 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 | $0.00017 | $0.04296 |
| Opus 5 | $0.00009 | $0.02148 |
| Sonnet 5 | $0.00003 | $0.00859 |
| Haiku 4.5 | $0.00002 | $0.00430 |
Grade A, and why
graph 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 2d 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb graph
Show graph data (nodes, edges, automatic communities, Topics, and edge types) for visualization. The graph can be generated at document level (one node per file) or chunk level (one node per chunk within each file), then scoped by a folder or analyzed through a named Shard.
Usage
mdvdb graph [OPTIONS]
Arguments
This command takes no arguments.
Options
| Flag | Short | Default | Description |
|---|---|---|---|
--level |
document |
Graph granularity level: document or chunk |
|
--path |
Restrict visible graph topology to this collection-relative folder | ||
--shard |
Use a configured Shard as the graph analysis context | ||
--compact |
false |
With --json, emit the versioned compact wire format; alias --intern-contexts |
--level <LEVEL>
Controls the granularity of the graph nodes.
| Level | Description |
|---|---|
document (default) |
One node per indexed file. Edges are body links and frontmatter Relations between files. Clusters are document-level communities. |
chunk |
One node per chunk within each file. Edges are the top-k most similar chunk pairs across different files (based on cosine similarity of embeddings). Intra-file edges are excluded. |
At document level, edges come from body links and whole-value frontmatter Relations. At chunk level, edges come from embedding similarity (the top 5 most similar cross-file chunks for each chunk).
--path <PREFIX>
Restricts the graph to files whose paths start with the given prefix. Only nodes matching the prefix are included, and only edges between matching nodes are returned.
# Graph only for files under docs/
mdvdb graph --path docs/
# Graph only for API documentation
mdvdb graph --path docs/api/
--shard <ID>
Uses the named Shard as an independent analysis corpus. Only indexed documents below the Shard folder participate in automatic clustering, and only that Shard's local Topic definitions are used. Collection, parent-Shard, and sibling Topics do not leak into the response.
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.
- 2d ago First seen · 453 lines · 17 tokens per session scan A 10fdd55dc245
graph is a command published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 18d ago), licensed MIT. It adds 17 tokens to every session and 4,296 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
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…
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.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
web-search
Search fetched web-source Markdown by regex and pull surrounding context for the best hits. Optionally restrict to one source alias.
docs-refresh
Re-fetch a cached source, ignoring the 7-day cache. Use when upstream content has changed.