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-thinkgit 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-think)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-think"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-think/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-think"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-think.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 | $0.00110 | $0.01313 |
| Opus 5 | $0.00055 | $0.00656 |
| Sonnet 5 | $0.00022 | $0.00263 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
phoenix-think 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-think — understand deeply, then define "done" objectively
The most expensive bug is building the wrong thing correctly.
Most agents skip straight to code on a half-understood ask and produce something plausible but wrong.
phoenix-think is the antidote: it spends cheap thinking-tokens up front to (1) extract what the user
actually wants, (2) ground it in real evidence from the codebase and the world, and (3) crystallize
it into an intent whose finish line is a runnable objective check — the gate the rest of the
Phoenix lifecycle (plan → build → review → ship) verifies against. No check, no proceed.
This stage is deliberately rich. Rushing it is the false economy this whole harness exists to prevent.
Three movements (do them in order; loop until clarity)
1. ELICIT — Socratic deep interview (extract intent, don't assume it)
Ask one focused question at a time, each targeting the highest-uncertainty unknown. Prefer questions that expose hidden assumptions over questions that confirm what you already believe. Cover, as relevant:
- Outcome: What does success look like to you? How will you know it worked? (push for an observable signal, not a feeling)
- Boundaries: What is explicitly OUT of scope? What must NOT change or break?
- Constraints: performance, privacy, budget (calls/$), reversibility, deadline, who else is affected.
- Context & priors: Is there existing code, a convention, a past attempt, a preferred approach?
- Edge cases & failure: What inputs/states worry you? What does "wrong" look like?
- Hidden assumptions: State the assumptions you're making back to the user and ask them to confirm or correct each one. ("I'm assuming X — is that right?")
Track an informal ambiguity score: how much could still go wrong if you executed now? Keep interviewing until that risk is low. Stop early if the user says "just do it" — respect their intent, but state the top 1–2 assumptions you're proceeding 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.
- 11d ago First seen · 87 lines · 110 tokens per session scan A 270fabed0fb9
phoenix-think is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 6d ago), licensed MIT. It adds 110 tokens to every session and 1,313 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
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.
plan-validate
Deterministic plan.json validation via Python script, replacing most plan-validator agent calls. Performs JSON parsing, schema validation, task checkbox regex, required section checks, sync validation, and data extraction. Only semantic consistency checks (storage/query alignment) require the LLM agent. Triggers on…