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.
git clone --depth 1 https://github.com/ExaDev/agent-commsWrote 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/plugins/exadev/agent-comms/marketplace)<a href="https://agentmods.dev/plugins/exadev/agent-comms/marketplace"><img src="https://agentmods.dev/badge/plugins/exadev/agent-comms/marketplace/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/plugins/exadev/agent-comms/marketplace"><img src="https://agentmods.dev/badge/plugins/exadev/agent-comms/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-comms marketplace 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.
What it actually says
{
"metadata": {
"description": "Cross-harness communication mesh for LLM agents",
"homepage": "https://github.com/ExaDev/agent-comms#readme"
},
"name": "agent-comms",
"owner": {
"name": "ExaDev"
},
"plugins": [
{
"description": "Cross-harness LLM agent communication mesh — rooms, DMs, and presence",
"name": "agent-comms",
"source": {
"source": "url",
"url": "https://github.com/ExaDev/agent-comms.git"
},
"version": "8.13.20"
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
1 file beside marketplace.json 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.
- 5d ago Changed c2490c5909b7
- 9d ago Changed cd4247ba05e1
- 10d ago Changed 667e47006343
- 11d ago Changed 679d74ce6764
- 13d ago Changed 3e3923e15401
- 14d ago Changed 08255b3e5291
- 15d ago Changed 4d861f824816
- 16d ago Changed 0938ce27d1fd
- 23d ago Changed af6c040f4196
- 24d ago First seen · 22 lines scan A 3487a4f0154d
agent-comms marketplace is a plugin published in the GitHub repository ExaDev/agent-comms (31 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
decocms-ui
Build UI with the decocms product design system (@decocms/ui).
atlan
Atlan context layer plugin for Claude Code. Search, explore, govern, and manage your data assets through natural language. Powered by the Atlan MCP server with semantic search, lineage traversal, glossary management, data quality rules, and more.
rpikit
rpikit. A Claude Code plugin implementing the Research-Plan-Implement (RPI) framework for disciplined software engineering.
core-numerical
All core numerical skills.
code-review
Automated code review for pull requests using multiple specialized agents with confidence-based scoring.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.