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/edgesgit 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 | $0.00013 | $0.02084 |
| Opus 5 | $0.00006 | $0.01042 |
| Sonnet 5 | $0.00003 | $0.00417 |
| Haiku 4.5 | $0.00001 | $0.00208 |
Grade A, and why
edges 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvdb edges
Show semantic edges between linked files. Semantic edges are enriched link connections that include the paragraph context surrounding each link, an embedding-based similarity score (strength), and an auto-discovered relationship type label derived from edge clustering. This command displays the full catalog of semantic edges in the index, with optional filtering by file or relationship type.
Usage
mdvdb edges [FILE] [OPTIONS]
Arguments
| Argument | Required | Description |
|---|---|---|
FILE |
No | Filter edges to those involving this file (as source or target). Relative path, e.g., docs/api.md. |
When FILE is provided, only edges where the specified file is the source or the target are returned. When omitted, all semantic edges in the index are shown.
Options
| Flag | Short | Default | Description |
|---|---|---|---|
--relationship |
Filter edges by relationship type (case-insensitive substring match on the cluster label) |
--relationship <TYPE>
Filters edges to only those whose auto-discovered relationship type label contains the given substring (case-insensitive). Relationship types are generated from edge clustering during ingestion -- they are TF-IDF keyword labels describing groups of semantically similar edges.
For example, --relationship "api" would match edges with relationship types like "api-reference", "API Documentation", or "rest-api-endpoints".
If no edges match the filter, an empty result is returned.
Global Options
These options apply to all commands. See Commands Index for details.
| Flag | Short | Description |
|---|---|---|
--verbose |
-v |
Increase log verbosity (-v info, -vv debug, -vvv trace) |
--root |
Project root directory (defaults to current directory) | |
--no-color |
Disable colored output | |
--json |
Output results as JSON |
Human-Readable Output
When run without --json, edges displays a formatted list of semantic connections:
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 · 208 lines · 13 tokens per session scan A 67cb89f6d6f8
edges is a command published in the GitHub repository geckse/markdown-vdb (23 stars, last pushed 18d ago), licensed MIT. It adds 13 tokens to every session and 2,084 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.