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/watchgit clone --depth 1 https://github.com/geckse/markdown-vdbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/geckse/markdown-vdb/watch)<a href="https://agentmods.dev/commands/geckse/markdown-vdb/watch"><img src="https://agentmods.dev/badge/commands/geckse/markdown-vdb/watch.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00013 | $0.01502 |
| Opus 5 | $0.00006 | $0.00751 |
| Sonnet 5 | $0.00003 | $0.00300 |
| Haiku 4.5 | $0.00001 | $0.00150 |
Grade A, and why
watch 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 5d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb watch
Watch configured source folders and apply incremental updates when Markdown files are created,
modified, renamed, or deleted. The watcher also observes the project-root
.markdownvdb.schema.yml so Formula, Lookup, Rollup, and Relation definitions can react without a
manual restart.
Usage
mdvdb watch [GLOBAL OPTIONS]
There are no command-specific flags. Common forms are:
mdvdb watch
mdvdb watch --root /path/to/project
mdvdb watch --json
mdvdb watch -vv --no-color
--json is a long-lived NDJSON stream: one startup object followed by one object per processed
event.
Incremental behavior
Every event is serialized through the project module lock so raw index changes, computed-field evaluation, Markdown writeback, and the final save remain one coherent operation.
| Change | Work performed |
|---|---|
| Duplicate/no-op filesystem event | Skip when both source and embedding-body hashes still match |
| Frontmatter-only edit | Refresh metadata, Relations, schemas, and computed modules without embedding, FTS, or cluster work |
| Body create/change | Parse, chunk, adaptively embed, update vector/FTS data, links/Relations, schemas, collection clusters/Topics, then Formula and Lookup/Rollup |
| Delete | Remove vector/FTS/link and collection analysis state, refresh schemas, and run dependent modules |
| Rename | Remove the old identity, index the new identity, and report both paths |
| Schema overlay edit | Refresh global/scoped schemas and relation classification, then run modules with schema_changed; no embedding call |
Formula runs before Lookup/Rollup. Successful computed values are atomically materialized into declared frontmatter keys; bodies and unrelated YAML are preserved. The filesystem echo caused by that writeback is recognized as a no-op, preventing a watch loop.
Automatic collection clusters and compatible collection Topic assignments are updated
incrementally. New or changed Topic definitions, and Shard-local Topic state, can still require a
collection-wide mdvdb ingest.
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.
- 5d ago First seen · 186 lines · 13 tokens per session scan A 0fed5a2c06af
watch is a command published in the GitHub repository geckse/markdown-vdb (24 stars, last pushed 21d ago), licensed MIT. It adds 13 tokens to every session and 1,502 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
add-performance-monitoring
Setup application performance monitoring.
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.
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.