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/configgit 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 | $0.02058 |
| Opus 5 | $0.00005 | $0.01029 |
| Sonnet 5 | $0.00002 | $0.00412 |
| Haiku 4.5 | $0.00001 | $0.00206 |
Grade A, and why
config 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb config
Inspect the resolved runtime configuration, update a YAML setting by dotted path, or manage a supported provider secret without putting its value in process arguments.
Usage
mdvdb config [OPTIONS]
mdvdb config [OPTIONS] set <KEY> <VALUE>
mdvdb config [OPTIONS] unset <KEY>
mdvdb config [OPTIONS] secret set <NAME> --stdin
mdvdb config [OPTIONS] secret unset <NAME>
Commands and options
| Command | Description |
|---|---|
set <KEY> <VALUE> |
Set a project YAML value using a dotted key path |
unset <KEY> |
Remove a project override so an inherited value or default applies |
secret set <NAME> --stdin |
Read a supported secret from stdin and store it |
secret unset <NAME> |
Remove a stored secret |
| Option | Description |
|---|---|
--global |
Target user configuration instead of this Collection for mutations |
--root <PATH> |
Use another Collection root |
--json |
Serialize the resolved configuration when no mutation command is supplied |
-v, -vv, -vvv |
Increase logging detail |
--no-color |
Disable colored human output |
--global changes the mutation target. With no subcommand, mdvdb config --global still shows the
fully merged runtime configuration for the selected Collection.
Inspect resolved settings
mdvdb config
mdvdb --json config
mdvdb --root /path/to/collection config
Human output is a compact operational summary: provider, model, configured dimensions, batch size, source directories, chunking, search, watch, clustering, and the user config path. It does not attribute each setting to its source.
JSON output serializes the complete resolved runtime Config, using runtime field names such as
embedding_provider, clustering_algorithm, and topics_min_similarity:
mdvdb --json config \
| jq '{provider: .embedding_provider,
model: .embedding_model,
dimensions: .embedding_dimensions,
clustering: .clustering_algorithm}'
For embedding.dimensions: auto, config JSON remains "auto". The concrete dimension resolved
from an existing index or a live inference appears in mdvdb status or mdvdb embedding probe;
it is not written back into YAML.
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 · 249 lines · 11 tokens per session scan A c09489c8c00d
config 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 2,058 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
wiki-init
Initialize a new LLM Wiki in the current directory. Creates the full directory structure, config, and template files.
check-invariants
Runs only the tree CRDT invariant test battery in outl-core. Faster than /check, focused on what can break sync.
claude-cmd-status
A Claude Code slash command. OpenCode does not read Claude commands.
docs-refresh
Re-fetch a cached source, ignoring the 7-day cache. Use when upstream content has changed.
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.
voice-setup
Interactive setup for human voice configuration.