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-setupgit 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-setup)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-setup"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-setup/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-setup"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-setup.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 | $0.00077 | $0.00521 |
| Opus 5 | $0.00039 | $0.00260 |
| Sonnet 5 | $0.00015 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
phoenix-setup 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 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.
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
/phoenix-setup
This skill installs ATV-Phoenix into the GitHub Copilot CLI so the phoenix agent and its four
self-healing tools become available.
What it does
- Ensures the Rust binary
phoenix-mcpexists (builds it withcargo build --releaseif missing). - Registers the
phoenixMCP server in~/.copilot/mcp-config.json(so the tools auto-load). - Installs the
phoenixagent definition to~/.copilot/agents/phoenix.agent.md(socopilot --agent phoenixworks after a restart). - Installs the 13 bundled skills into
~/.copilot/skills, then self-checks them withphoenix-mcp doctor(the harness validates its own skills). - Installs the bundled TokenMasterX for token-efficient retrieval (best-effort; needs
graphify).
How to run it
The setup script ships in this skill's directory. Locate it, then run it with the repo root:
- Run
/skills info phoenix-setupand read the skill's directory path from the output. - Run the setup script, passing the skill dir and the repo root:
python <skill-dir>/setup.py --repo <ATV-Phoenix-repo-root>
If --repo is omitted, the script looks for the repo via the PHOENIX_REPO env var or the current
directory. It prints exactly what it registered and the restart command.
After install
Restart Copilot (or start with copilot --agent phoenix). Then ask Copilot to verify and self-heal a
task — it will call phoenix_sense / phoenix_heal and only report success on objective evidence.
Honesty
The tools report objective signals only (exit codes / hashes / regex). A fabricated "done" is the failure mode Phoenix prevents; "I'm not sure it passed" is acceptable.
What ships with it
1 file beside SKILL.md 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.
- 9d ago First seen · 40 lines · 77 tokens per session scan A b21c14a2e882
phoenix-setup is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 521 once invoked, about $0.0004 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
learning-quality
Structured format for capturing high-quality learnings during ClosedLoop runs.