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/facesgit 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/faces)<a href="https://agentmods.dev/commands/erhangundogan/videre/faces"><img src="https://agentmods.dev/badge/commands/erhangundogan/videre/faces.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 | $0.00018 | $0.03254 |
| Opus 5 | $0.00009 | $0.01627 |
| Sonnet 5 | $0.00004 | $0.00651 |
| Haiku 4.5 | $0.00002 | $0.00325 |
Grade A, and why
faces 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 3d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detects faces, then groups them so you can name a person once instead of tagging each photo.
videre faces # detect, group, and store (resumable)
videre faces --limit 500 # only process 500 new images, then stop
videre faces --recluster # regroup existing faces without re-detecting
videre faces --reprocess # start over: re-detect everything
videre faces --dry-run # detect but write nothing
videre faces --profile # print per-stage timing when finished
videre faces --silent # no per-image progress
videre faces --db ~/photos.db # use a specific database
videre faces --ext heic # only HEIC photos
videre faces --date 2024-07 # only that month
:::tip These filters work the same way across commands, and combine. See scoping a run. :::
The first run downloads about 180 MB, separate from the search model.
The whole workflow
Detection and naming are separate steps. The first is slow and automatic, the second is fast and manual.
videre faces # 1. find faces and group them (slow, resumable)
videre gallery # 2. name the groups in your browser
videre search --person "Alice"
Step 2 opens localhost:7878; naming happens on its People tab
(/people), which has three sections: People you have named, Unassigned
Clusters (groups it is confident about but has no name for), and Singletons
(faces it could not group). Drag a cluster onto a person to assign it, or create
a new person from it.
Clicking a cluster or a person opens its own page, at /people/cluster/<id> and
/people/person/<name>.
The payoff is the ratio: one drag can name forty photos.
Working through a large library
Detection on tens of thousands of photos takes hours. --limit lets you do it
in sittings:
videre faces --limit 2000 # a chunk, then stop
videre faces --limit 2000 # continue where it left off
videre faces --recluster # once, after the last chunk
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.
- 3d ago First seen · 286 lines · 18 tokens per session scan A 65036fcd1261
faces is a command published in the GitHub repository erhangundogan/videre (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 18 tokens to every session and 3,254 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
graph
Generate an interactive visual graph of your memories. Powered by graphify (github.com/safishamsi/graphify, MIT).
brand-generate
Generate an on-brand document from a saved Brand Profile.
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.