ATV-Phoenix: Agent for Claude Code

.github/agents/phoenix-cloud-worker.agent.md

phoenix-cloud-worker is an agent for Claude Code from All-The-Vibes/ATV-Phoenix. It costs 17 tokens per session (220 once invoked), scanned B, original, MIT.

A cloud-worker agent for making limited Phoenix code changes and checking the results. Phoenix is the project or system whose changes it handles.

In plain words
What is it for?
Use it for bounded Phoenix edits, baseline and snapshot checks, targeted verification, rollback or retry recovery, and final trace verification.
Why use it?
It provides recorded checks before and after edits, helping confirm that a change worked without weakening acceptance tests or hiding failures.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is All-The-Vibes/ATV-Phoenix's own configuration. It tells Claude Code how to work on ATV-Phoenix 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 ATV-Phoenix configures →

Reuse

Borrowing it

Nothing to install: this file belongs to All-The-Vibes/ATV-Phoenix. 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/All-The-Vibes/ATV-Phoenix/main/.github/agents/phoenix-cloud-worker.agent.md
Clone the repo
git clone --depth 1 https://github.com/All-The-Vibes/ATV-Phoenix

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 phoenix-cloud-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker/github.svg)](https://agentmods.dev/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker)
Your own site
<a href="https://agentmods.dev/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker"><img src="https://agentmods.dev/badge/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker/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 phoenix-cloud-worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker"><img src="https://agentmods.dev/badge/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 220 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00017 $0.00220
Opus 5 $0.00009 $0.00110
Sonnet 5 $0.00003 $0.00044
Haiku 4.5 $0.00002 $0.00022

Measured 9d ago against content hash a5f82ef1b2e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

phoenix-cloud-worker scanned grade B with 1 finding 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 9d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ['*']
.github/agents/phoenix-cloud-worker.agent.md · 25 lines

What it actually says

Use Phoenix checks as objective evidence rather than judging your own work. Establish a green baseline with phoenix_sense, snapshot before risky edits, and sense the relevant acceptance check after each bounded change. Never weaken, replace, or skip a frozen acceptance check.

If a check fails, use only bounded rollback or retry recovery and trust its external recheck. Run phoenix_verify_trace before reporting success, and report any failed or unavailable proof honestly. Keep edits within the requested scope and do not add unrelated automation.

Return branch evidence: branch name, concise diff summary, exact checks run and their results, and the trace verification result.

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. 9d ago First seen · 25 lines · 17 tokens per session scan B a5f82ef1b2e1

Subscribe to this mod's changes

phoenix-cloud-worker is an agent published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 220 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.