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.
curl -O https://raw.githubusercontent.com/All-The-Vibes/ATV-Phoenix/main/.github/agents/phoenix-cloud-worker.agent.mdgit clone --depth 1 https://github.com/All-The-Vibes/ATV-PhoenixWrote 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/agents/all-the-vibes/atv-phoenix/phoenix-cloud-worker)<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.
<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>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.
| Model | Per session | Once 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 |
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: ['*'] 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.
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.
- 9d ago First seen · 25 lines · 17 tokens per session scan B a5f82ef1b2e1
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.
Other agents, from other repositories
pre-explorer
Pre-explores codebase before plan drafting. Produces requirements-extract.json, code-map.json, and investigation-log.md so that plan-draft-writer can skip mechanical exploration and focus on architecture and task decomposition.
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
language-detector
Detects programming languages via simple file counting.
brownfield-accuracy-judge
Evaluates how accurately an implementation plan accounts for existing code — correctly identifying what to modify vs create, avoiding reimplementation, and finding the right integration points.
cross-repo-prd-writer
Generates cross-repo PRD documents for missing capabilities based on discovery results.