metadata-fixer

metadata-fixer is a skill for Claude Code from drolosoft/immich-photo-manager. It costs 127 tokens per session (2,255 once invoked), scanned A, original, MIT.

A tool for finding and correcting missing or suspicious photo details such as dates, locations, time zones, and camera information. EXIF is the technical information stored inside many image files.

In plain words
What is it for?
It helps inspect an Immich photo library and suggest corrections using nearby photos, folder structure, and information inferred from the images.
Why use it?
It helps repair errors caused by imports or folder-based date recovery, including midnight timestamps and missing GPS data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the immich-photo-manager plugin — 13 skills, 5 commands shipped together

Good fit It helps inspect an Immich photo library and suggest corrections using nearby photos, folder structure, and information inferred from the images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/drolosoft/immich-photo-manager/metadata-fixer
Install

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.

Any agent
npx skills add drolosoft/immich-photo-manager --skill metadata-fixer
Clone the repo
git clone --depth 1 https://github.com/drolosoft/immich-photo-manager

Made for: Claude Code.

Or install immich-photo-manager, the plugin that ships this one along with the rest of its 13 skills, 5 commands.

Wrote 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.

agentmods badge for metadata-fixer

README.md
[![agentmods](https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/metadata-fixer/github.svg)](https://agentmods.dev/skills/drolosoft/immich-photo-manager/metadata-fixer)
Your own site
<a href="https://agentmods.dev/skills/drolosoft/immich-photo-manager/metadata-fixer"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/metadata-fixer/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.

agentmods 80×15 button for metadata-fixer

Your own site · 80×15
<a href="https://agentmods.dev/skills/drolosoft/immich-photo-manager/metadata-fixer"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/metadata-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00127 $0.02255
Opus 5 $0.00063 $0.01128
Sonnet 5 $0.00025 $0.00451
Haiku 4.5 $0.00013 $0.00226

Measured 6d ago against content hash 925df3bb5408, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

metadata-fixer 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 6d 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.

skills/metadata-fixer/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metadata Fixer

⚠️ Connection Required: ALWAYS CHECK FIRST

Before doing ANYTHING else in this skill, call ping on the Immich MCP server.

  • If ping succeeds → proceed with the skill normally.
  • If ping fails or the MCP tools are not available → STOP. Do not continue. Tell the user:

Immich is not connected. This plugin needs a running Immich MCP server to work.

Run /setup-immich-photo-manager to configure your Immich connection. You'll need:

  1. Your Immich server URL (e.g., http://192.168.1.100:2283)
  2. An Immich API key (how to create one)
  3. The MCP server configured (see /setup-immich-photo-manager)

Nothing in this plugin will work until the connection is configured.

Do NOT skip this check. Do NOT try to run any other tool first. Always ping, always block if it fails.

Scan an Immich library for broken, missing, or suspicious metadata and propose corrections. Focuses on the most impactful fields: dates, GPS coordinates, and timezone offsets.

Why This Matters

Common metadata problems in imported photo libraries:

  • Noon/midnight timestamps: dates recovered from folder paths lose the time component, defaulting to 00:00 or 12:00
  • Missing GPS: some export tools strip GPS data, or photos taken in airplane mode have none
  • Wrong timezones: photos taken abroad may have the wrong timezone offset, putting them hours off
  • No EXIF dates: screenshots, downloaded images, and some messaging apps strip date metadata entirely

Analysis Workflow

Step 1: Scan for Issues

Over the API: walk the library with get_timeline_buckets(), then get_timeline_bucket(time_bucket) for the months to check. Each row carries the asset date, city and country, which is enough to spot exact-noon and exact-midnight timestamps and the days where some photos have a place and others do not. get_asset_info fills in the rest for a candidate.

Read the full file on GitHub · 218 lines

Changes

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.

  1. 6d ago Changed 925df3bb5408
  2. 7d ago Changed · +15 lines b9ecaff2cea7
  3. 11d ago First seen · 203 lines · 127 tokens per session scan A a02350f4b146

Subscribe to this mod's changes

metadata-fixer is a skill published in the GitHub repository drolosoft/immich-photo-manager (47 stars, last pushed 7d ago), licensed MIT. It adds 127 tokens to every session and 2,255 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

ideogram-ultra

Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.

artokun/comfyui-mcp · 68 tokens

ltxv2-video

Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base models.

artokun/comfyui-mcp · 65 tokens

video-extend

Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatchpusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into…

artokun/comfyui-mcp · 146 tokens

director

Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation.

artokun/comfyui-mcp · 32 tokens

ernie-image

Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT…

artokun/comfyui-mcp · 98 tokens

model-compatibility

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.

artokun/comfyui-mcp · 47 tokens