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 skills/smart-ai-memory/attune-ai/image-analysisnpx skills add Smart-AI-Memory/attune-ai --skill image-analysisgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/skills/smart-ai-memory/attune-ai/image-analysis)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/image-analysis"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/image-analysis.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 5.1 | $0.00053 | $0.00630 |
| Opus 5 | $0.00026 | $0.00315 |
| Sonnet 5 | $0.00011 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
image-analysis 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Analysis
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="image-analysis", mode="preamble") and
display the returned preamble text as a blockquote. Then tell the
user they can say "tell me more" for a step-by-step guide, or answer
the scoping question below to proceed.
If the MCP call fails, fall back to:
Image Analysis — Sends an image (screenshot, diagram, UI mockup, chart) to Claude's vision model and returns a description or answers a question about it. Supports PNG, JPEG, GIF, and WebP.
Scoping
Before running, ask:
- Image path: "Which image file should I analyze?"
- Focus (optional): "Anything specific to look for, or a general description?"
Execution
Shared command workspace (preferred)
Open adapter image-analysis with the local image path and optional prompt.
The adapter reads the real file, validates repository containment, the 10MB
limit, magic bytes versus extension, dimensions, MIME type, and SHA-256. The
invocation already authorizes this read-only analysis, so the running workspace
has no synthetic confirmation action.
Call analyze_image with the validated path and publish the exact response as
analysis_result; include provider progress only as optional progress
events. Success requires non-empty analysis and must match the canonical MIME
and file size. Decode/provider failure must say “did not complete,” never
render an empty successful analysis. Present the terminal widget or Markdown,
and preserve the same input fingerprint and truthfulness in text fallback.
Call the analyze_image MCP tool:
Parameters:
- image_path (required): Path to the image file (PNG, JPEG, GIF, or WebP).
- prompt (optional): A specific question or instruction. Omit for a general description.
analyze_image(image_path="docs/architecture.png")
analyze_image(
image_path="screenshot.png",
prompt="What error is shown in this dialog?",
)
Output
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.
- 2d ago Changed · +15 lines f32882e5261c
- 6d ago First seen · 65 lines · 53 tokens per session scan A 8d19e2933459
image-analysis is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 630 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
story-setup
网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录，支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式：/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。.
novel-writing-assets
查看、启用、停用、组合、绑定、试写和重新编译 novel-studio 的长期写法资产。触发：「列出写法特征」「启用/停用某个写法」「组合写法」「绑定写法」「试写写法」「重编译写法规则」「维护写法资产」。.
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.