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/erhangundogan/videre/configgit clone --depth 1 https://github.com/erhangundogan/videreWrote 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/erhangundogan/videre/config)<a href="https://agentmods.dev/commands/erhangundogan/videre/config"><img src="https://agentmods.dev/badge/commands/erhangundogan/videre/config.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 | $0.00015 | $0.01584 |
| Opus 5 | $0.00008 | $0.00792 |
| Sonnet 5 | $0.00003 | $0.00317 |
| Haiku 4.5 | $0.00002 | $0.00158 |
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 4d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shows what every path and setting currently resolves to, and changes the three defaults that let you run other commands with fewer arguments.
videre config # show where everything resolves to
videre config set db ~/photos.db # use this database by default
videre config set path ~/Photos # scan this folder when none is given
videre config set model google/siglip-base-patch16-224 # default search model
videre config unset db # go back to the default database
videre config unset model # go back to the built-in search model
videre config unset path # require a folder argument again
Reading the output
home: ~/.videre
config: ~/.videre/config.toml
db: (not set) [set with: videre config set db <path>]
resolved db: ~/.videre/hashes.db
resolved path: ~/Photos [from config.toml]
model: google/siglip-base-patch16-224 (default) [set with: videre config set model <id>]
jsonl: ~/.videre/hashes.jsonl
| Line | Meaning |
|---|---|
home |
The directory holding everything. Follows VIDERE_HOME if set |
config |
Where the settings file lives, inside that home |
db |
Your configured default, or (not set) with the command to set it |
resolved db |
What commands will actually use right now |
resolved path |
The folder scan and watch use with no argument |
model |
The resolved search model, marked (default) when not configured |
read-rate |
Assumed floor read speed in MB/s, used to scale the file-read timeout to file size. Default 20. Only worth changing on a mount slower than that |
xmp |
Default XMP precedence for scan/watch: db, file, or newest. Default db. See videre mark |
export-xmp-on-watch |
Whether videre watch runs the XMP export stage each cycle. Default off |
jsonl |
Where a bare scan --output would write |
The distinction between db and resolved db is the useful part. The first is
what you set; the second is what you get, including the fallback when you have
set nothing. When something reads the wrong library, this is the line to check.
[from config.toml] marks a value that came from your settings rather than a
built-in default.
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.
- 4d ago First seen · 146 lines · 15 tokens per session scan A 17b8cd5e514e
config is a command published in the GitHub repository erhangundogan/videre (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,584 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 2026-08-31.
Other commands, from other repositories
deslop
Check the diff against main, and remove all AI generated slop introduced in this branch.
contrib
Profile how top GitHub contributors work — ingest, build personas, and synthesise a capability model + learnable playbook.
memory-init
Initialize local memory store + vector index for this project.
graph
Generate an interactive visual graph of your memories. Powered by graphify (github.com/safishamsi/graphify, MIT).
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.