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/initgit 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 | $0.00007 | $0.01002 |
| Opus 5 | $0.00003 | $0.00501 |
| Sonnet 5 | $0.00001 | $0.00200 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
init 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb init
Create a YAML configuration for a collection or for user-wide defaults.
Usage
mdvdb init [--global]
| Flag | Effect |
|---|---|
--global |
Create user defaults at ~/.mdvdb/config.yaml instead of project config |
The standard global flags also apply. Use mdvdb --root <PATH> init to initialize a different
collection root.
Project initialization
Run init at the root of a Markdown collection:
cd my-notes
mdvdb init
It creates .markdownvdb/config.yaml with a starter configuration equivalent to:
embedding:
provider: openai
model: text-embedding-3-small
dimensions: auto
batch_size: 100
search:
limit: 10
min_score: 0.0
mode: hybrid
rrf_k: 60.0
chunking:
max_tokens: 512
overlap_tokens: 50
clustering:
enabled: true
rebalance_threshold: 50
watch:
enabled: true
debounce_ms: 300
sources:
dirs: [.]
Unwritten settings retain built-in defaults, including Leiden as the automatic clustering algorithm. Edit the YAML directly or use dotted scalar updates such as:
mdvdb config set embedding.provider ollama
mdvdb config set embedding.model nomic-embed-text
mdvdb config set embedding.dimensions auto
After the first ingest, the directory also contains generated index data:
.markdownvdb/
├── config.yaml
├── index
└── fts/
Features such as Shard-local analysis may later add a disposable cache/ directory.
init creates configuration only. It does not scan, embed, or index files; run mdvdb ingest
after configuring a provider.
User defaults
mdvdb init --global
This creates ~/.mdvdb/config.yaml, or $MDVDB_CONFIG_HOME/config.yaml when
MDVDB_CONFIG_HOME is set. The generated file is intentionally minimal:
# Values here apply unless project config.yaml overrides them.
# Credentials belong in .env, not YAML.
# embedding:
# provider: openai
# model: text-embedding-3-small
# dimensions: auto
User YAML supplies defaults. Project .markdownvdb/config.yaml is deep-merged over it, and shell
MDVDB_* overrides have the highest settings priority.
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 · 168 lines · 7 tokens per session scan A fd6785dd9ea8
init is a command published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 18d ago), licensed MIT. It adds 7 tokens to every session and 1,002 once invoked, about $0.0000 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.