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-intentgit 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-intent)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-intent"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-intent/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-intent"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-intent.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 | $0.00119 | $0.02171 |
| Opus 5 | $0.00060 | $0.01086 |
| Sonnet 5 | $0.00024 | $0.00434 |
| Haiku 4.5 | $0.00012 | $0.00217 |
Grade A, and why
phoenix-intent 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 10d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-intent — decompose → N verified goals → composite proof
phoenix-goal handles one goal with one acceptance check. Many real tasks are multi-faceted
— "build the connector, integrate it, configure the scheduler, and notify the team" — with
parallel independent sub-goals and sequential dependencies. phoenix-intent is the orchestration
layer (hand it to phoenix-mission when you want the independent goals actually run concurrently):
decompose → validate all RED → execute (dependency-ordered) → prove composite done
The composite acceptance gate is satisfied only when all N goals are individually proven failure-first: each saw_red AND green_after_red AND currently_green on its own intact trace. No shortcut. No self-report.
The flow
vague intent ("build and ship the feature, notify the team")
│
▼ FRAME + confirm ── restate intent, decompose into N goals (≤5), invite correction
│
▼ FORMALIZE each goal ── one phoenix_sense acceptance check per goal (must start RED)
│ write .phoenix-intent/intent.json
│
▼ BASELINE ── run `phoenix-mcp sense` for EACH goal check (per-goal PHOENIX_WORKSPACE)
│ ALL must be RED — any green check is vacuous, re-target it
│
▼ EXECUTE ── per-goal phoenix-ralph loop (PHOENIX_WORKSPACE=.phoenix-intent/<goal_id>)
│ unordered where depends_on=[], ordered where dependencies exist
│ (use phoenix-mission to have the order enforced rather than assumed)
│
▼ COMPOSITE PROOF ── `phoenix-mcp intent-accept .phoenix-intent/intent.json`
ok=true only when ALL goals saw_red + green_after_red + green_now
The manifest (intent.json)
{
"intent": "wire the Teams notification into the daily pipeline and verify end-to-end",
"goals": [
{
"id": "build-connector",
"title": "Build the Teams connector module",
"kind": "build",
"check": { "kind": "command_exit", "target": ["cargo", "test", "--", "teams"], "expect": 0 },
"depends_on": []
},
{
"id": "configure-webhook",
"title": "Wire the webhook endpoint into the pipeline config",
"kind": "configure",
"check": { "kind": "regex_in_file", "target": ["config/pipeline.toml"], "expect": "teams_webhook" },
"depends_on": ["build-connector"]
},
{
"id": "notify-team",
"title": "Send a test Teams notification and confirm receipt",
"kind": "notify",
"check": { "kind": "command_exit", "target": ["node", "scripts/verify-teams.mjs"], "expect": 0 },
"depends_on": ["configure-webhook"]
}
]
}
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.
- 10d ago First seen · 171 lines · 119 tokens per session scan A 0aaf98c9a732
phoenix-intent is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 6d ago), licensed MIT. It adds 119 tokens to every session and 2,171 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…