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.
npx skills add All-The-Vibes/ATV-Phoenix --skill phoenix-doctorgit 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/skills/all-the-vibes/atv-phoenix/phoenix-doctor)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-doctor"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-doctor/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/skills/all-the-vibes/atv-phoenix/phoenix-doctor"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-doctor.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 | $0.00113 | $0.01612 |
| Opus 5 | $0.00056 | $0.00806 |
| Sonnet 5 | $0.00023 | $0.00322 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
phoenix-doctor 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-doctor — verify the install, then heal it
Overview
Phoenix is a self-healing harness; phoenix-doctor points that discipline at Phoenix's own install.
It compares the installed agent, skills, and MCP registration against what THIS build ships (embedded
in the phoenix-mcp binary), reports any drift with objective evidence, and --fix re-syncs from the
shipped reference — then re-runs the same check so a repair only counts when it goes red→green. It also
checks the running binary itself is built from the current source, so it can't be fooled by its own truth
being out of date. This
is the antidote to the whole class of "I installed it a while ago and something's off" problems: you never
guess, you compare to the source of truth.
When to use
copilot --agent phoenixsays "No such agent: phoenix" (or it's missing from the list).- A
/phoenix-*skill is missing, stale, or behaving differently than the docs say. - Right after upgrading / re-pulling Phoenix, to confirm the install matches the new build.
- Any "is my install healthy?" question.
How to run it
1. Diagnose (cheap, offline — no auth, no model):
phoenix-mcp doctor
Prints a JSON InstallReport plus a human summary, and exits non-zero if anything is wrong. Each check is
shaped like a phoenix_sense result — {check, ok, evidence, problems} — so the signal is objective.
2. Repair (idempotent, snapshot-backed):
phoenix-mcp doctor --fix
Re-syncs the agent + any missing/drifted skills from the shipped reference and re-registers the MCP server,
backing up the prior agent/mcp-config as *.doctor-bak first, then re-verifies. Safe to re-run; a clean
install is a no-op.
3. Authoritative load test (--deep, needs the CLI + auth):
The drift check tells you the file matches the source of truth; the load test proves the CLI actually
accepts it. After a fix, confirm with the real loader:
copilot --agent phoenix -p "reply READY" -s --allow-all-tools
"No such agent" (red) → "READY" (green) is the end-to-end proof the repair worked. Run this against the
same home you fixed (--home/$COPILOT_HOME if non-default).
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.
- 12d ago First seen · 93 lines · 113 tokens per session scan A 6bfe725ee772
phoenix-doctor is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 8d ago), licensed MIT. It adds 113 tokens to every session and 1,612 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
semgrep-rule-creator
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.
variant-analysis
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.
vuln-report
Turn one confirmed security finding into a disclosure-ready GitHub advisory with root cause, proof of concept, impact, and source evidence. Use for reporting an established vulnerability, not discovering or validating one.
fp-check
Systematically verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug.
huggingface-spaces
Build, deploy, debug, or maintain a Hugging Face Space using Gradio, Docker, or Static SDKs. Use for general Space hosting and configuration; use huggingface-zerogpu for ZeroGPU runtime constraints and lora-space-builder for LoRA demos.
decision-table
Use when the user wants a code-grounded decision table for current behavior, wants to compare current behavior against a plan or work item, or needs a control-flow artifact for recovery, retry, finalization, validation, state-machine, or review-heavy edge cases.