AgentConnect is an open-source platform that lets teams and multiple AI agents collaborate in shared conversations and work processes across services such as Slack, Telegram, Discord, GitHub, GitLab, and Linear. Teams use it to assign agents roles, have agents call one another, and start work from messages, issues, pull requests, webhooks, or schedules.
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 agentconnect-md/agentconnect --skill agentconnect-imagesgit clone --depth 1 https://github.com/agentconnect-md/agentconnectWrote 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/agentconnect-md/agentconnect/agentconnect-images)<a href="https://agentmods.dev/skills/agentconnect-md/agentconnect/agentconnect-images"><img src="https://agentmods.dev/badge/skills/agentconnect-md/agentconnect/agentconnect-images/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/agentconnect-md/agentconnect/agentconnect-images"><img src="https://agentmods.dev/badge/skills/agentconnect-md/agentconnect/agentconnect-images.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 | $0.00060 | $0.00763 |
| Opus 5.5 | $0.00024 | $0.00305 |
| Sonnet 5.5 | $0.00012 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
agentconnect-images 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating and sharing images
This skill is a workflow, not an image engine. You create the image with capabilities
your runtime already exposes; AgentConnect's shareFile tool then shows it to the
person you are talking to. If shareFile is not among your tools in this conversation,
describe the result in words instead.
1. Create the image
- Illustrations, photos, edits: use a native image-generation capability or an image tool that is already configured in this session. Check what you actually have; do not assume a tool exists because of your model or runtime name.
- Charts and technical diagrams: use the plotting or rendering tools available to you
(for example a Python plotting library) when that fits the request. Produce PNG, JPEG,
WEBP or a self-contained static SVG, and keep any editable source (script, notebook,
.drawio, …) next to it. - Never silently substitute a plotted diagram for a requested illustration. If the person asked for a generated picture and you cannot generate one, say so.
If no generation capability is available, explain which capability is missing. Do not invent a tool name, install a provider, ask for new credentials on your own, or claim that AgentConnect can call tools that only exist inside another runtime.
2. Save it in the workspace
- Save the finished original inside your workspace, preferably under
outputs/images/with a unique, descriptive name such asoutputs/images/product-illustration-2.png. - A generator may hand you bytes, a temporary path or a download link. Use your file or network tools to put the result in the workspace first; a file outside the workspace cannot be shared.
- If you can inspect images, look at the result before sharing it.
3. Share it
Call shareFile with the workspace-root-relative path and an optional short caption:
{ "path": "outputs/images/product-illustration.png", "caption": "Product illustration" }
- Your working directory may be a subdirectory; the path is always relative to the workspace root.
- One call shares one image. Several images need several calls.
- The result is a short receipt (
"type": "agentconnect.image","published": true). The person already sees an image card with View original and Download. - After a successful share, do not repeat the image as Markdown and do not paste download URLs into your reply. A reply that is only the image is fine; add text only when it helps.
- Static SVG is accepted only when it is self-contained: no scripts, event handlers, external references, entities or embedded HTML.
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.
- 5d ago First seen · 68 lines · 60 tokens per session scan A d9e0796531e3
agentconnect-images is a skill published in the GitHub repository agentconnect-md/agentconnect (1,465 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 763 once invoked, about $0.0002 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 2026-10-11.
Other skills, from other repositories
security-audit
Perform a security audit on code, checking for common vulnerabilities including injection, auth bypass, secrets leakage, and unsafe dependencies.
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.
openma
Use the openma platform to build, deploy, and manage AI agents. Trigger when users want to create agents, start sessions, manage environments, configure model cards, handle vaults/credentials, install skills, connect MCP servers, or interact with the openma HTTP API. Also trigger when users mention "oma", "openma"…