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/big-emotion/agent-atelierWrote 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/big-emotion/agent-atelier/agent-comms)<a href="https://agentmods.dev/plugins/big-emotion/agent-atelier/agent-comms"><img src="https://agentmods.dev/badge/plugins/big-emotion/agent-atelier/agent-comms/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/big-emotion/agent-atelier/agent-comms"><img src="https://agentmods.dev/badge/plugins/big-emotion/agent-atelier/agent-comms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-comms 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 today.
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
{
"name": "agent-comms",
"displayName": "Agent Comms",
"version": "0.2.0",
"description": "Communication skills for short-form video and social publishing: attention-architect writes the script and names the mechanism behind every beat, video-director carries the production decisions and the traps that have already cost time, audience-audit measures what the audience actually does, content-strategist decides what to publish next and where, bigemotion-reel-clip turns a translated interview excerpt into a captioned LinkedIn clip. The idea and structure-carousel packs and a studio kit (validators, a guide-mode prompt renderer and answer parser) let a product run the chain as steps with fixed deliverables.",
"author": {
"name": "Big Emotion"
},
"homepage": "https://github.com/big-emotion/agent-atelier",
"repository": "https://github.com/big-emotion/agent-atelier",
"license": "MIT",
"keywords": ["communication", "video", "social", "audience", "content-strategy", "attention", "carousel", "studio"]
}
What it installs
The manifest is a name and a version. 9 skills travel with it, and installing the plugin installs all of them — 883 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill audience-audit A 122 tokens
- Skill bigemotion-reel-clip A 150 tokens
- Skill idea A 137 tokens
- Skill structure-carousel A 125 tokens
- Skill structure-reel A 115 tokens
- Skill structure-image A 97 tokens
- Skill attention-architect A 0 tokens
- Skill content-strategist A 137 tokens
- Skill video-director A 0 tokens
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.
- today Changed 01972310989f
- 10d ago Changed d1d521960cca
- 1mo ago First seen · 14 lines scan A 026e7b274fe8
agent-comms is a plugin published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 2d 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 2026-09-08.
Other plugins, from other repositories
privacy-guard
Keeps private infrastructure details out of public repositories. Ships the privacy-guard skill: session rules for what must never cross the public boundary, plus a per-repo pre-commit gate built on a gitignored local denylist and gitleaks. The denylist is never committed, so the hook is a no-op for external…
toonify-mcp
Local context compression for Claude Code workflows, including structured data and debug-heavy output.
nyann
Project governance for Claude Code. Bootstrap and maintain git workflow, hooks, commits, releases, CI, docs, and repo health.
deploygate
DeployGate agent integration: upload mobile apps, manage distribution pages, set up CI/CD, and onboard your team. Supports iOS (IPA) and Android (APK/AAB).
claudeconf
Research-driven, technology-agnostic harness generator for Claude Code: pinned, standard-tool quality + security pipelines (git hooks, CI, e2e, gates, supply-chain admission, agent-hardening) plus a read-only harness-doctor agent.
ci-incident-medic
Triages failing GitHub Actions runs, hardens Dockerfiles, pre-flights Kubernetes manifests before they reach the cluster, and drafts blameless postmortems from incident evidence.