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/markgit 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/mark)<a href="https://agentmods.dev/commands/erhangundogan/videre/mark"><img src="https://agentmods.dev/badge/commands/erhangundogan/videre/mark.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 | $0.00018 | $0.00995 |
| Opus 5 | $0.00009 | $0.00498 |
| Sonnet 5 | $0.00004 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
mark 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marks a photo: a star rating, a keeper/reject pick, a colour label, or a like
(favourite). Marks 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 mark --person "Alice" --location Berlin --rating 5 # set on a selection
videre mark --category screenshot --pick reject # cull candidates
videre mark --path ~/Photos/2024 --label red --like
videre search --rating 5 | videre mark --like # target by piping paths in
Setter flags
At least one is required (otherwise there is nothing to do).
| Flag | Sets | Clear with |
|---|---|---|
--rating <0-5> |
star rating (0 clears) |
--rating 0 |
--pick <keep|reject|none> |
pick (keeper / reject) | --pick none |
--label <colour|none> |
colour label | --label none |
--like / --no-like |
like (favourite) | --no-like |
pick and like are two different axes on purpose: pick reject is a culling
decision (cull this), like is a positive favourite. There is no "dislike",
because it would just duplicate reject.
Choosing what to mark
Targets come from either the selection flags or a pipe:
- Selection flags narrow the library the same way
searchdoes:--person,--date/--after/--before,--location/--radius,--type,--ext,--mime,--path. See scoping a run. - Standard input: if you pipe paths in (
videre search ... | videre mark ...), those files are marked. This is how you mark by an existing mark, since the mark flags onmarkitself always set rather than filter.
A run prints N of M, so a filter matching nothing is distinguishable from an
empty library. With no selection and no pipe, every file is marked.
Finding photos by mark
The same names are filters on videre search (and in the
gallery), composing with everything else:
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.
- 3d ago First seen · 93 lines · 18 tokens per session scan A 439374bb0585
mark 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 995 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.