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/getgit 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 | $0.00015 | $0.01022 |
| Opus 5 | $0.00008 | $0.00511 |
| Sonnet 5 | $0.00003 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
get 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb get
Retrieve index metadata for one Markdown document. The command reports its frontmatter, computed values and diagnostics, chunk count, file size, content hash, and timestamps.
Usage
mdvdb get [OPTIONS] <FILE_PATH>
| Name | Required | Description |
|---|---|---|
<FILE_PATH> |
Yes | Project-relative path as stored in the index |
--populate |
No | Resolve frontmatter relations and reverse references, one level deep |
The command also accepts all global options, including --json and --root.
Examples
# Inspect metadata
mdvdb get docs/api.md
# Include resolved relation targets and documents that reference this file
mdvdb get invoices/invoice-104.md --populate
# Machine-readable output
mdvdb get invoices/invoice-104.md --populate --json
JSON output
{
"path": "invoices/invoice-104.md",
"content_hash": "a1b2c3d4e5f67890...",
"frontmatter": {
"title": "Invoice 104",
"client": "[[clients/acme]]",
"price": 120,
"quantity": 2,
"total": 240
},
"computed_fields": {
"total": 240
},
"computed_field_errors": {},
"chunk_count": 3,
"file_size": 712,
"indexed_at": 1770000100,
"modified_at": 1770000000,
"relations": {
"client": [
{
"raw": "[[clients/acme]]",
"path": "clients/acme.md",
"exists": true,
"title": "Acme",
"frontmatter": {
"title": "Acme",
"domain": "acme.example"
}
}
]
},
"referenced_by": [
{
"source": "payments/payment-104.md",
"field": "invoice",
"title": "Payment 104"
}
]
}
Fields
| Field | Type | Description |
|---|---|---|
path |
string |
Project-relative document path |
content_hash |
string |
SHA-256 hash used for change detection |
frontmatter |
object | null |
Parsed, materialized YAML frontmatter; authoritative value surface |
computed_fields |
object |
Successful Formula, Lookup, and Rollup values mirrored for provenance |
computed_field_errors |
object |
Diagnostics keyed by computed field name |
chunk_count |
number |
Number of indexed text chunks |
file_size |
number |
File size in bytes |
indexed_at |
number |
Unix timestamp of the last ingest |
modified_at |
number | null |
Filesystem modification timestamp |
relations |
object |
Resolved frontmatter relations; present only with --populate |
referenced_by |
array |
Reverse frontmatter references; present only with --populate |
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 · 122 lines · 15 tokens per session scan A 9502d19116a5
get is a command published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 18d ago), licensed MIT. It adds 15 tokens to every session and 1,022 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.
wiki-digest
Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.
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.
demo-command
Example slash command that wraps the demo-skill. Showcases the command kind.