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/clustersgit 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 | $0.00011 | $0.01877 |
| Opus 5 | $0.00005 | $0.00938 |
| Sonnet 5 | $0.00002 | $0.00375 |
| Haiku 4.5 | $0.00001 | $0.00188 |
Grade A, and why
clusters 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb clusters
Inspect automatic document communities or manage user-defined Topics. Without a Shard, results use
the Collection analysis stored in the shared index. With --shard, automatic communities and
Topic assignments belong only to that named recursive sub-collection.
Usage
mdvdb clusters [--shard <ID>]
mdvdb clusters [--shard <ID>] --custom
mdvdb clusters [--shard <ID>] list
mdvdb clusters [--shard <ID>] add <NAME> [OPTIONS]
mdvdb clusters [--shard <ID>] update <NAME> [OPTIONS]
mdvdb clusters [--shard <ID>] remove <NAME>
mdvdb clusters [--shard <ID>] unassigned
Options
| Flag | Description |
|---|---|
--shard <ID> |
Use the Shard's independent automatic clusters and Topics |
--custom |
Show computed Topic summaries instead of automatic clusters |
Topic definition options:
| Flag | Applies to | Description |
|---|---|---|
--description <TEXT> |
add, update |
Natural-language Topic description |
--seeds <A,B,...> |
add, update |
Comma-separated seed phrases |
--threshold <VALUE> |
add, update |
Per-Topic similarity threshold in 0.0..1.0; on update, a negative value clears the override |
--rename <NAME> |
update |
Rename the Topic within its owner |
A Topic must have a non-empty description, at least one seed, or both. Names are unique case-sensitively within their owner. The Collection and every Shard are separate owners, so two scopes may intentionally use the same name with different definitions and assignments.
Automatic clusters
# Communities across the complete Collection
mdvdb clusters
# Finer communities derived only from indexed documents in Research
mdvdb clusters --shard research
Collection automatic clusters are built by ingest and updated incrementally by watch when a
compatible state exists. Shard automatic clusters are computed lazily from the existing document
vectors already stored in the shared index. They use the
Collection's clustering algorithm and settings but only the Shard corpus. For Leiden analysis,
clustering.knn remains the configured upper bound; a Shard caps its effective neighborhood at
max(2, ceil(sqrt(document_count))). This prevents a small Shard from becoming a complete
similarity graph and collapsing otherwise useful local communities. Collection clustering is
unchanged.
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 · 227 lines · 11 tokens per session scan A dbd81c13b453
clusters is a command published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 18d ago), licensed MIT. It adds 11 tokens to every session and 1,877 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.