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/importgit 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/import)<a href="https://agentmods.dev/commands/erhangundogan/videre/import"><img src="https://agentmods.dev/badge/commands/erhangundogan/videre/import.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 | $0.00016 | $0.01792 |
| Opus 5 | $0.00008 | $0.00896 |
| Sonnet 5 | $0.00003 | $0.00358 |
| Haiku 4.5 | $0.00002 | $0.00179 |
Grade A, and why
import 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brings a library in from somewhere else: a Google Takeout export, an Apple Photos or iPhoto library, or an Adobe Lightroom catalog. It works out what you pointed it at, finds the actual files, and corrects the dates those tools left behind.
videre import ~/Pictures # find whatever is in there
videre import ~/Takeout # a Google Takeout export
videre import ~/Pictures/Photos\ Library.photoslibrary
videre import # search the usual places
The bare path is the main form. You do not need to know whether you have a
.photoslibrary, a .lrcat or a Takeout dump, and you do not need to know
where inside it the files are kept.
Where it looks for files
Every source resolves file locations through the same ladder, stopping at the first step that works:
| Step | What it tries |
|---|---|
| 1 | The provider's own catalog. Only when you pass --use-library-db, or for Lightroom, where there is no alternative |
| 2 | Known folder layouts: originals/, Masters/, Originals/, Google Photos/ |
| 3 | Asks you, via --originals <dir> |
The default never opens a provider database. Apple, in particular, is read purely from the filesystem, because Apple's schema changes between macOS releases and its folder layout does not.
Each run reports which step succeeded, so you can see how your files were found:
Located 46,118 file(s) via originals/ (catalog not read).
Apple renamed that folder twice, so all three spellings are recognised: early
iPhoto used Originals/, iPhoto 9 used Masters/, and Photos on Mojave and
later uses lowercase originals/ with a hex fan-out.
When it cannot find them
If a vendor changes their structure in a version newer than your videre, you are
not stuck. --originals overrides every step:
videre import --originals ~/somewhere/photos ~/Pictures/Odd.photoslibrary
Options
| Option | Effect |
|---|---|
--originals <dir> |
Where the files actually are. Overrides every detection step |
--use-library-db |
Also read the provider's catalog to locate files. Off by default |
--allow-partial |
Proceed without prompting when an Apple library looks optimised |
--dry-run |
Report what would change, modify nothing |
-y, --yes |
Skip the confirmation prompts |
--silent |
No per-file output. Errors always show |
--json |
One JSON summary object on stdout |
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 · 189 lines · 16 tokens per session scan A fb1221c9c54e
import is a command published in the GitHub repository erhangundogan/videre (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,792 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.