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 phoenixgit 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)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix/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"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix.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 | $0.00092 | $0.02527 |
| Opus 5 | $0.00046 | $0.01264 |
| Sonnet 5 | $0.00018 | $0.00505 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
phoenix 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 6d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phoenix — the self-healing engineering harness (meta-skill)
Phoenix is a comprehensive engineering workflow, organized by development phase, where every phase
ends in an objective verification gate (phoenix_sense) and every failure triggers bounded
recovery (phoenix_heal). It is built to be fast and extremely token-efficient: it routes
structural questions to a prebuilt code graph instead of re-reading files, loads skill detail only when
a phase activates (progressive disclosure), and never burns tokens looping on unverified work.
The orchestration layer — not the model — determines agent success. Phoenix is that layer.
Skill routing
Task arrives
│
├── Vague / "not sure what I want" / high-stakes? ───→ phoenix-think (deep interview + research)
├── Have a clear intent, need steps? ────────────────→ phoenix-plan (verifiable task breakdown)
├── Implementing code? ──────────────────────────────→ phoenix-build (snapshot→edit→sense→heal)
│ ├── proving behavior / fixing a bug? ──────────→ phoenix-test (the test is the gate)
│ ├── writing TypeScript? ───────────────────────→ phoenix-typescript (tsc --noEmit is the gate)
│ ├── building/reviewing UI or animation? ───────→ phoenix-design (taste, gated by build/lint)
│ ├── dependencies / a CVE / a lockfile? ────────→ phoenix-deps (clean-room install is the gate)
│ └── keeping it simple & surgical? ─────────────→ phoenix-craft (Karpathy guardrails)
├── Something broke / a check is red? ───────────────→ phoenix-debug (triage + self-heal)
├── Need cheap, precise context on a big codebase? ──→ phoenix-context (graph routing, −tokens)
├── Reviewing finished work? ────────────────────────→ phoenix-review (re-run every check + trace)
└── Declaring done / shipping? ──────────────────────→ phoenix-ship (final sense + verified trace)
A task usually flows think → plan → build (↔ test/debug) → review → ship, but enter at whatever phase matches reality. Skills also activate by their own descriptions — building UI pulls build+test, a red check pulls debug, and so on.
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.
- 6d ago Changed · +1 lines 6d0b659dc68f
- 10d ago First seen · 148 lines · 92 tokens per session scan A d126a473ef3f
phoenix is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 2,527 once invoked, about $0.0005 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.