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/exportgit clone --depth 1 https://github.com/erhangundogan/videreWhat 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 | $0.00022 | $0.00794 |
| Opus 5 | $0.00011 | $0.00397 |
| Sonnet 5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
export 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writes the labels you built in videre into standard .xmp sidecar files next to
your photos, so other tools (digiKam, Lightroom, darktable) can read them. This
is how videre stops being an island: the work you invested in naming faces,
rating and labelling travels with your library instead of living only in
hashes.db.
Opt-in and non-custodial: it only ever writes a .xmp sidecar beside the file,
and never modifies the original.
videre export --xmp # every file with something to write
videre export --xmp --path ~/Photos/2024 # just one folder
videre export --xmp --person "Ayşe" # just photos of one person
videre export --xmp --dry-run # list what would be written
What it writes
For each selected photo, videre writes the labels it owns into one sidecar, using the standard fields the other tools already read:
| videre data | XMP field |
|---|---|
| Named faces (confirmed) | MWG face regions (mwg-rs:Regions), name plus box |
| Resolved location name | Iptc4xmpCore:Location |
| Category (photo/screenshot/document/meme) | dc:subject keyword |
| Tags | dc:subject keywords |
| Star rating | xmp:Rating |
| Colour label | xmp:Label |
Face regions are written as normalized MWG areas, the format digiKam and Lightroom use for face tags, so a name you assigned in videre shows up as a named face region there. Picks and likes have no portable standard and stay in videre's database.
A file with nothing to write gets no sidecar.
Merging, not clobbering
If a sidecar already exists (for example one Lightroom wrote), videre merges: it replaces only the fields it owns and preserves everything else in the file verbatim, including another tool's keywords and develop settings. Re-exporting is safe and idempotent.
Choosing what to export
The selection flags narrow the library exactly as videre search
does: --path, --person, --date/--after/--before,
--location/--radius, --type, --ext, --mime, --category. See
scoping a run. With no selection, every file with
something to write gets a sidecar.
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 · 77 lines · 22 tokens per session scan A 06b7250acffd
export is a command published in the GitHub repository erhangundogan/videre (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 22 tokens to every session and 794 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.