Pipecat is an open-source Python framework for building real-time conversational agents that work with voice, video, images, and other media. It is for creating voice assistants, companions, business agents, and multi-agent systems from modular conversation pipelines.
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/pipecat-ai/pipecatWrote 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/pipecat-ai/pipecat/pipecat-dev)<a href="https://agentmods.dev/plugins/pipecat-ai/pipecat/pipecat-dev"><img src="https://agentmods.dev/badge/plugins/pipecat-ai/pipecat/pipecat-dev/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/pipecat-ai/pipecat/pipecat-dev"><img src="https://agentmods.dev/badge/plugins/pipecat-ai/pipecat/pipecat-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pipecat-dev 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 1mo 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
{
"name": "pipecat-dev",
"description": "Development workflow skills for contributing to the Pipecat project",
"version": "1.0.0",
"source": "./",
"skills": [
"./.claude/skills/changelog",
"./.claude/skills/cleanup",
"./.claude/skills/code-review",
"./.claude/skills/docstring",
"./.claude/skills/pr-description",
"./.claude/skills/pr-submit",
"./.claude/skills/prose-review",
"./.claude/skills/provider-research",
"./.claude/skills/provider-research-digest",
"./.claude/skills/squash-commits",
"./.claude/skills/update-docs"
]
}What it installs
The manifest is a name and a version. 11 skills travel with it, and installing the plugin installs all of them — 231 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill update-docs A 16 tokens
- Skill cleanup A 17 tokens
- Skill docstring A 13 tokens
- Skill pr-description A 26 tokens
- Skill provider-research A 48 tokens
- Skill prose-review A 28 tokens
- Skill changelog A 13 tokens
- Skill provider-research-digest A 42 tokens
- Skill squash-commits A 0 tokens
- Skill code-review A 14 tokens
- Skill pr-submit A 14 tokens
What ships with it
1 file beside marketplace.json#pipecat-dev 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.
- 1mo ago First seen · 19 lines scan A 8c4b06e814ca
pipecat-dev is a plugin published in the GitHub repository pipecat-ai/pipecat (16,618 stars, last pushed today), licensed BSD-2-Clause. 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 2026-09-03.
Other plugins, from other repositories
fix-all
Run bin/claude-review --print and automatically fix all reported issues, committing each fix individually.
han-github
Github specific extensions to the Han plugin for agentic planning and coding. Provides skills to post code reviews as PR comments, update a PR description with a consistent format, etc.
odin-git
ODIN workflows for commits, branches, pull requests, review feedback, and issue tracking.
git
Git workflow tools: commits, PRs, review inbox, checkout, and work triage.
review-toolkit
Comprehensive PR review pipeline: a pre-review readiness gate (stops on merge conflicts or red code-related CI with a fix-it note, no verdict), branch-level analysis with merge-base attribution (the verdict is decided only by defects the diff introduced, worsened, or interacts with — purely pre-existing defects are…
git-pr
Committing, PR creation and review triage, and dependency upgrades.