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.
git clone --depth 1 https://github.com/danielrosehill/Claude-Image-Production-PluginWrote 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/danielrosehill/claude-image-production-plugin/group-by-time)<a href="https://agentmods.dev/commands/danielrosehill/claude-image-production-plugin/group-by-time"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-image-production-plugin/group-by-time/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/danielrosehill/claude-image-production-plugin/group-by-time"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-image-production-plugin/group-by-time.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00560 |
| Opus 5.5 | $0.00000 | $0.00224 |
| Sonnet 5.5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
group-by-time 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 2mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Group Images by Capture Time
Cluster images by EXIF DateTimeOriginal into year / month (and optionally day) folders.
Task
-
Ask which folder to operate on — default is the current working directory. Confirm recursion; default flat.
-
Confirm granularity with the user:
YYYY/onlyYYYY/MM/(default)YYYY/MM/DD/- Custom (e.g. session-based, gap > N hours starts a new group)
-
Read capture timestamps for each image. Prefer, in order:
exiftoolDateTimeOriginalexiftoolCreateDate/MediaCreateDateexiftoolFileModifyDate(fallback — warn the user when falling back, since mtime reflects copy time)
exiftool -s -s -s -DateTimeOriginal -CreateDate -FileModifyDate "image.jpg" -
Build a timeline — sorted (filename, timestamp) list. Show the user min/max timestamps and any suspicious gaps / duplicates.
-
Propose grouping — print bucket labels (
2026/04/,2026/04/18/) with image counts. Flag any file that fell back to mtime. Let the user rename buckets (e.g.2026-04-18_wedding/). -
Preview before acting, then choose method:
- Option A:
metadata/time-groups.csvwithfilename,timestamp,group(no moves) - Option B: symlinked folders (
time-groups/2026/04/photo.jpg → ../../../photo.jpg) - Option C: physical move on explicit confirmation
- Option A:
-
Log to
notes/group-by-time-{timestamp}.md:- Granularity used
- Bucket labels and counts
- Files that fell back to mtime (flagged for review)
- Files with no usable timestamp at all (bucketed to
unknown-date/)
Notes
- Timezone matters. If EXIF lacks a TZ offset, ask the user which TZ to assume (and record it in the log). Default to the system TZ (Israel IST/IDT here).
- For mixed-source imports (phone + camera + screenshots), timestamps from different devices may drift — flag clips that cluster oddly.
- Never mutate originals. Prefer the CSV manifest for archives with many files.
- Files with no EXIF and no reliable mtime go to
unknown-date/— don't invent a timestamp.
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.
- 2mo ago First seen · 44 lines · 0 tokens per session scan A d492a437b4a5
group-by-time is a command published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 560 tokens. 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 2026-08-30.
group-by-time compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| group-by-timedanielrosehill/Claude-Image-Production-Plugin | Command | 21 | yesterday | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |