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/locationsgit 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/locations)<a href="https://agentmods.dev/commands/erhangundogan/videre/locations"><img src="https://agentmods.dev/badge/commands/erhangundogan/videre/locations.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 5.1 | $0.00016 | $0.01259 |
| Opus 5 | $0.00008 | $0.00629 |
| Sonnet 5 | $0.00003 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
locations 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 5d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groups photos by where they were taken, using GPS coordinates
videre scan already extracted from EXIF. No network access:
place names come from an offline lookup.
videre locations # group and print a summary
videre locations --radius 25 # how far apart places can be, in km (default 15)
videre locations --json # print one JSON object instead
videre locations --geojson # print GeoJSON (opens in geojson.io, QGIS, ...)
videre locations --silent # no summary
videre locations --db ~/photos.db # use a specific database
:::note
Unlike other long-running commands, videre locations takes no
scoping filters. It rebuilds every cluster from
scratch on each run, so restricting it to part of the library would not do less
work, it would leave everything outside that part unclustered.
:::
The workflow
videre scan ~/Photos # GPS comes from EXIF during the scan
videre locations # group those coordinates into places
Output is a summary of the places found, largest first:
142 location cluster(s) found
Berlin, Germany 3,841 photos
Kreuzberg, Berlin, Germany 612 photos
Lisbon, Portugal 498 photos
...
Nothing else is required. GPS is already in the database after a scan, so this
does not depend on watch --location having run.
Choosing a radius
--radius is the only real tuning, and it decides what counts as one place:
| Radius | Groups look like |
|---|---|
| 2 to 5 km | Neighbourhoods and individual venues |
| 15 km (default) | Which city was I in |
| 50 to 100 km | Regions, metro areas |
| 300+ km | Countries, trips |
There is no correct value. A single holiday reads better at 5 km, a decade of photos at 15 or more. Since every run recomputes from scratch, trying another radius costs nothing but time.
videre locations --radius 5 # break a city into districts
videre locations --radius 200 # collapse a trip into one place
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.
- 5d ago First seen · 136 lines · 16 tokens per session scan A 0104e404220e
locations is a command published in the GitHub repository erhangundogan/videre (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,259 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).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.