pipecat: Agent for Claude Code

.claude/agents/provider-watch-researcher.md

provider-watch-researcher is an agent for Claude Code from pipecat-ai/pipecat. It costs 70 tokens per session (468 once invoked), scanned A, original, BSD-2-Clause.

A research worker for checking whether a Pipecat service provider offers new models or API options. Pipecat is a framework for building real-time voice and media applications.

In plain words
What is it for?
Use it to follow a provider-watch research guide, write a dated report, and prepare a committed branch for a possible draft pull request.
Why use it?
It gives a larger provider-monitoring workflow a focused worker for researching one provider and service type at a time.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

This is pipecat-ai/pipecat's own configuration. It tells Claude Code how to work on pipecat itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pipecat configures →

About the project

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.

pipecat-ai/pipecat · 15,374 stars · on GitHub · pipecat.ai

Reuse

Borrowing it

Nothing to install: this file belongs to pipecat-ai/pipecat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pipecat-ai/pipecat/main/.claude/agents/provider-watch-researcher.md
Clone the repo
git clone --depth 1 https://github.com/pipecat-ai/pipecat

Made for: Claude Code.

Wrote 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.

agentmods badge for provider-watch-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/pipecat-ai/pipecat/provider-watch-researcher/github.svg)](https://agentmods.dev/agents/pipecat-ai/pipecat/provider-watch-researcher)
Your own site
<a href="https://agentmods.dev/agents/pipecat-ai/pipecat/provider-watch-researcher"><img src="https://agentmods.dev/badge/agents/pipecat-ai/pipecat/provider-watch-researcher/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.

agentmods 80×15 button for provider-watch-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/pipecat-ai/pipecat/provider-watch-researcher"><img src="https://agentmods.dev/badge/agents/pipecat-ai/pipecat/provider-watch-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00468
Opus 5 $0.00035 $0.00234
Sonnet 5 $0.00014 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 7d ago against content hash 56ea20b787b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

provider-watch-researcher 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 7d 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.

.claude/agents/provider-watch-researcher.md · 26 lines

What it actually says

You research exactly one unit for one provider-watch run. The JSON payload in your prompt names the unit, the paths, the previous report and the decisions file.

Before doing anything else, read, in this order:

  1. .claude/skills/provider-research/RESEARCH_GUIDE.md — what to investigate, how to probe, when a PR is warranted, and the branch recipe.
  2. .claude/skills/provider-research/REPORT_TEMPLATE.md — the exact report shape.

Then follow the guide: read the memory (previous report, decisions, PR states), do the research, probes before claims, report written to the payload's report_file.

Hard rules:

  • Never modify or run git commands in repo_root other than read-only ones (git rev-parse, git fetch, git worktree add, gh pr list/view). All code changes happen in your own worktree under scratch_dir, exactly as the guide's branch recipe describes.
  • Never push and never call gh pr create / gh issue create. You propose a PR by leaving one committed branch; publishing happens outside the skill, through scripts/provider-watch/publish.py.
  • Never print, write, or return credentials, Authorization headers, or .env contents. Only probe.py talks to providers unless the guide's ad-hoc tier applies.
  • Keep the report concise; a current service gets a short report.

Your final message is parsed by a program: return exactly one JSON line — {"service", "default_model", "prs", "gaps", "error", "summary", "report_path"} — and nothing else. If something goes wrong, write the report with error set and still return the line.

Changes

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.

  1. 7d ago Changed · +1 tokens per session 56ea20b787b9
  2. 10d ago First seen · 26 lines · 69 tokens per session scan A 6551c2b988b4

Subscribe to this mod's changes

provider-watch-researcher is an agent published in the GitHub repository pipecat-ai/pipecat (15,374 stars, last pushed today), licensed BSD-2-Clause. It adds 70 tokens to every session and 468 once invoked, about $0.0003 per session on Opus 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 2026-08-30.