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/taggit 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/tag)<a href="https://agentmods.dev/commands/erhangundogan/videre/tag"><img src="https://agentmods.dev/badge/commands/erhangundogan/videre/tag.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 | $0.00017 | $0.00627 |
| Opus 5 | $0.00009 | $0.00313 |
| Sonnet 5 | $0.00003 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
tag 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 today.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tags a photo with any word or phrase you like. Tags are stored per photo (by
content hash, so they follow a photo across duplicates and moves) and compose
with every other filter in videre search.
videre tag --add beach --add summer --path ~/Photos/2024 # add on a selection
videre tag --add "to print" --person "Ayşe" --rating 5 # target by any filter
videre tag --remove beach --path ~/Photos/2024/blurry # remove
Setting tags
Give at least one --add or --remove (both are repeatable, and you may pass
both in one run: removals apply first, then additions).
| Flag | Effect |
|---|---|
--add <tag> |
Add this tag to every file in the selection |
--remove <tag> |
Remove this tag from every file in the selection |
Choosing what to tag
The selection flags narrow the library the same way search does: --person,
--category, --date/--after/--before, --location/--radius, --type,
--ext, --mime, --path, --has, --missing. See
scoping a run. A run prints N of M. With no
selection, every file is tagged.
There is no --tag filter here: on this command a tag means set, not filter.
To retag by an existing tag, select the files another way.
Finding photos by tag
--tag is a filter on videre search, composing with
everything else. It is repeatable and ANDed: every named tag must be present.
videre search --tag beach
videre search --tag beach --tag summer --person "Ayşe" --rating 4
Portability
Tags round-trip through standard XMP dc:subject keywords: a scan reads keywords
from a photo's sidecar or embedded packet and stores them as tags, and
videre export --xmp writes your tags back out as
dc:subject, so digiKam, Lightroom and darktable see them. Hierarchical
keywords (lr:hierarchicalSubject) are not modelled yet; a tag is one flat
string, and a /-separated value is stored verbatim.
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.
- today Changed · +1 lines 4cfb50ab32df
- 5d ago First seen · 61 lines · 17 tokens per session scan A f06c5e35da25
tag is a command published in the GitHub repository erhangundogan/videre (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 627 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.