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 skills add 7df-lab/devo --skill attach-imagegit clone --depth 1 https://github.com/7df-lab/devoWrote 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/7df-lab/devo/attach-image)<a href="https://agentmods.dev/skills/7df-lab/devo/attach-image"><img src="https://agentmods.dev/badge/skills/7df-lab/devo/attach-image/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/skills/7df-lab/devo/attach-image"><img src="https://agentmods.dev/badge/skills/7df-lab/devo/attach-image.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 | $0.00074 | $0.00422 |
| Opus 5.5 | $0.00030 | $0.00169 |
| Sonnet 5.5 | $0.00015 | $0.00084 |
| Haiku 4.5 | $0.00007 | $0.00042 |
Grade A, and why
attach-image 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- attach-image — 100% identical, 0 lines differ
What it actually says
Attach Image
Load on-disk images into the model's context as multimodal attachments. The image is sent to the model the same way a pasted image is, so the model can actually look at it.
When to use this
- The user points at an image file and wants you to look at it.
- You need to read text, a chart, a diagram, or a layout from an image.
- A screenshot needs visual interpretation.
When NOT to use this
For programmatic work on an image — measuring pixels, cropping, resizing, computing a hash, comparing files byte-by-byte — open it in the kernel with a library instead:
from PIL import Image
img = Image.open("diagram.png")
print(img.size)
That path does not put the image in the model's context; it only lets you
compute over it. Use attach_image when you need to see the image.
Usage
Call the prepared attach_image import directly in the Python kernel:
print(await attach_image("diagram.png"))
print(await attach_image("a.png", "b.jpg"))
The skill automatically resizes and compresses large images before loading them into context. Animated images that need compression are flattened to their first frame. Transparent images that need compression are composited onto a neutral gray background. Extremely large images are rejected by pixel count before full processing. The original file is left untouched.
Supported formats: PNG, JPEG, GIF, WebP. The skill errors if a file is not a supported image, or if the current model is not vision-capable.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 50 lines · 74 tokens per session scan A 0939d6ecbfc7
attach-image is a skill published in the GitHub repository 7df-lab/devo (321 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 422 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
codex-pr-body
Update the title and body of one or more pull requests.
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
remote-tests
Testing against remote executors in integration tests.
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.