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-depsgit 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-deps)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-deps"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-deps/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-deps"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-deps.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 | $0.00106 | $0.02010 |
| Opus 5 | $0.00053 | $0.01005 |
| Sonnet 5 | $0.00021 | $0.00402 |
| Haiku 4.5 | $0.00011 | $0.00201 |
Grade A, and why
phoenix-deps scanned grade A 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 7d 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 accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
the resolution pass, review what changed, *then* install for real. Install hooks execute arbitrary code Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-deps — a dependency change is a supply-chain decision, and it needs a gate
Encodes the practice from
jongio/skills→deps-doctor(MIT). That skill states the two hard rules as craft. Phoenix's contribution is to make them gates, because a rule an agent can talk its way past is not a rule.
Overview
Everywhere else, Phoenix refuses to let an agent grade its own work. Dependencies are the one surface where "I updated the packages" has historically been accepted on assertion. It shouldn't be — a dependency bump is not a version edit, it is a decision to run someone else's new code inside your build.
So the gate is not "the manifest changed". The gate is that the regenerated lockfile installs clean in a fresh environment the way CI will, and the test suite is still green after it.
The gate
{"check":{"kind":"command_exit","target":["npm","ci"],"expect":0}}
Per-ecosystem equivalents — always the clean-room form, never the incremental one, because an incremental install passes on a lockfile CI will reject:
| ecosystem | gate command |
|---|---|
| npm / pnpm / yarn | npm ci · pnpm install --frozen-lockfile · yarn install --immutable |
| Python | uv sync --locked · pip install -r requirements.txt in a fresh venv |
| Rust | cargo build --locked |
| Go | go mod verify && go build ./... |
| .NET / Java | dotnet restore --locked-mode · mvn -B verify |
Run the install gate and the test gate. A lockfile that resolves but breaks the suite is red.
The loop
inventory every manager ──► audit ──► is there a real change? ──no──► STOP. Report. No branch, no PR.
│ (the no-op boundary)
yes
▼
resolve with lifecycle scripts DISABLED
│
▼
review every package whose version or source changed
│
▼
install for real ──► clean-room install gate (phoenix_sense)
│ │
green red
│ ▼
│ fix FORWARD — never --force, never downgrade
│ │
▼ ▼
test gate ──────────────► re-sense
│
▼
report, naming every manager that came back BLOCKED
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.
- 7d ago First seen · 138 lines · 106 tokens per session scan A 4e22c94e517f
phoenix-deps is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 6d ago), licensed MIT. It adds 106 tokens to every session and 2,010 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
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…