agentmods.dev

gallery-qa

gallery-qa is a skill for Claude Code, Codex from OPPO-Mente-Lab/X-OmniClaw. It costs 29 tokens per session (813 once invoked), scanned A, original, Apache-2.0.

A guide for answering questions about photos in a device gallery using a complete image-memory file. The file records each image's filename, time, album, and short description.

In plain words
What is it for?
Use it to answer what was photographed, find images by time or topic, and copy matching photos to another folder or album.
Why use it?
It provides one complete source to search when identifying or organising gallery photos, rather than relying on incomplete results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 261repo +1 3mo ago A scan 29 tokens original Apache-2.0

Good fit Use it to answer what was photographed, find images by time or topic, and copy matching photos to another folder or album.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oppo-mente-lab/x-omniclaw/gallery-qa
View source ↗ OPPO-Mente-Lab/X-OmniClaw eggplant95.github.io
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 OPPO-Mente-Lab/X-OmniClaw --skill gallery-qa
Clone the repo
git clone --depth 1 https://github.com/OPPO-Mente-Lab/X-OmniClaw

Made for: Claude Code, Codex.

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 gallery-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/gallery-qa/github.svg)](https://agentmods.dev/skills/oppo-mente-lab/x-omniclaw/gallery-qa)
Your own site
<a href="https://agentmods.dev/skills/oppo-mente-lab/x-omniclaw/gallery-qa"><img src="https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/gallery-qa/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 gallery-qa

Your own site · 80×15
<a href="https://agentmods.dev/skills/oppo-mente-lab/x-omniclaw/gallery-qa"><img src="https://agentmods.dev/badge/skills/oppo-mente-lab/x-omniclaw/gallery-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 813 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.
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 $0.00029 $0.00813
Opus 5 $0.00015 $0.00407
Sonnet 5 $0.00006 $0.00163
Haiku 4.5 $0.00003 $0.00081

Measured 11d ago against content hash 55d0f4651f61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gallery-qa 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 11d 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.

app/src/main/assets/skills/gallery-qa/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill for all gallery-image consumption tasks, including:

  • 今天我拍了什么照片
  • 我最近拍过什么
  • 我拍过和猫有关的照片吗
  • 帮我把所有截图整理出来
  • 把猫主题图片复制到某个文件夹

This skill is the primary consumer of memory/IMAGE-MEMORY.md. It does not maintain or rebuild image memories. If the user explicitly asks to scan, sync, refresh, or rebuild image memories, use gallery-memory instead.

Source Of Truth

The source of truth is:

  • memory/IMAGE-MEMORY.md

Each entry is compact and should be read as one whole item:

  • title line: the image filename
  • time: capture or creation time
  • album: where the image lives in the gallery (MediaStore bucket / album display name)
  • summary: short semantic description

Core Workflow

When this skill applies, follow this workflow strictly:

  1. Load the full memory/IMAGE-MEMORY.md file into context with memory_get.
  2. Treat the entire file as the candidate set.
  3. Read the entries directly from top to bottom and find the entries relevant to the user request.
  4. For question answering, summarize the matched entries in natural language.
  5. For operations such as copy / move / add to folder / add to album, use the filename in each matched entry for later execution. Use album when the user asks which album or folder the image came from.

Hard Rules

  1. Do not start with retrieval or search when the full compact IMAGE-MEMORY.md file can be loaded directly.
  2. Do not treat image_memory_search_entries as the primary path. It is legacy.
  3. Do not use find as the primary topic filter when IMAGE-MEMORY.md already exists.
  4. Do not guess a wildcard filename prefix from the first few entries.
  5. Do not call gallery_memory unless the user explicitly asks to sync, scan, refresh, or rebuild image memories.

Answering Rules

  1. Do not answer with only file paths, line numbers, or entry ids.
  2. Use the summary field as the main semantic evidence.
  3. Use time when the user asks about today / yesterday / recent / date-scoped photos.
  4. If multiple images match, group or summarize them clearly.
  5. If the user asks for 所有 / 全部 / 都, inspect the whole file before finalizing.

Read the full file on GitHub · 94 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. 11d ago First seen · 94 lines · 29 tokens per session scan A 55d0f4651f61

Subscribe to this mod's changes

gallery-qa is a skill published in the GitHub repository OPPO-Mente-Lab/X-OmniClaw (261 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 813 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 2026-08-30.

LLMMemory and contextagentopenclaw-agent
Related

Other skills, from other repositories

browserwing-executor

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

MemTensor/MemOS · 42 tokens

memory-poisoning-detection

Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.

Tencent/AI-Infra-Guard · 33 tokens

dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…

MemTensor/MemOS · 84 tokens

ask-user-question

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

MemTensor/MemOS · 44 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

memos-memory-guide

Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query…

MemTensor/MemOS · 131 tokens