faces

faces is a command for coding agents from erhangundogan/videre. It costs 18 tokens per session (3,254 once invoked), scanned A, original, Apache-2.0.

A photo command that finds faces, groups similar faces, and lets you name each person once across the matching photos.

In plain words
What is it for?
Use it to detect and group people, process selected dates or file types, regroup existing results, or preview changes without saving them.
Why use it?
It avoids tagging the same person manually in every image and supports resumable processing for large photo collections.

Command

Install

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.

agentmods
npx agentmods add commands/erhangundogan/videre/faces
Clone the repo
git clone --depth 1 https://github.com/erhangundogan/videre

Wrote 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.

agentmods badge for faces

README.md
[![agentmods](https://agentmods.dev/badge/commands/erhangundogan/videre/faces.svg)](https://agentmods.dev/commands/erhangundogan/videre/faces)
Your own site
<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>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,254 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 65036fcd1261, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

docs/src/content/docs/commands/faces.md · 286 lines

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

Read the full file on GitHub · 286 lines

Changes

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.

  1. 3d ago First seen · 286 lines · 18 tokens per session scan A 65036fcd1261

Subscribe to this mod's changes

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.