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-missiongit 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-mission)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-mission"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-mission/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-mission"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-mission.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 | $0.00153 | $0.02241 |
| Opus 5 | $0.00077 | $0.01120 |
| Sonnet 5 | $0.00031 | $0.00448 |
| Haiku 4.5 | $0.00015 | $0.00224 |
Grade A, and why
phoenix-mission 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-mission — supervised DAG execution
phoenix-goal drives one goal. phoenix-intent decomposes an intent into N goals and proves the
composite. Neither one schedules: they run loops back to back and trust that nothing collides.
phoenix-mission is the scheduler. It takes goals with declared prerequisites and runs them under
the supervisor spine:
plan → admit under capacity → isolate → execute → ledger + chain → contain failure
Read this first: what capacity means
capacity is a real parallelism limit. Goals admitted together execute concurrently — one
thread per goal — and the supervisor never admits more than capacity at once. Four independent
goals at capacity: 4 run at the same time; at capacity: 1 they run one after another.
Only the goal's own work runs off the scheduler thread. Admission, leases, worktrees, budgets, the run ledger, and the hash-chained traces are all settled on the scheduler thread between batches — the chains are hash-linked, so concurrent appends would corrupt the record used to prove what happened.
With backend: "cloud", each goal is submitted and polled on its own thread, so cloud goals
genuinely overlap too.
What you get:
| Property | What it means |
|---|---|
| True concurrency | Up to capacity goals inside execute simultaneously |
| Dependency ordering | A goal runs only after every prerequisite succeeded |
| Contained failure | A failed goal blocks its dependents; unrelated branches still complete |
| Panic containment | A backend that panics fails its own goal; the mission still settles |
| Worktree isolation | Every executed goal gets an exclusive workspace path |
| Lease fencing | A stale holder cannot write over a goal it no longer owns |
| Budgets | Per-goal and mission-wide caps; the mission stops when the mission cap blows |
| Durable run ledger | One append-only entry per execution, with backend + cost + error |
| Per-goal trace chains | Each goal gets its own tamper-evident chain, verified independently |
| Cloud dispatch | Each goal can run on a GitHub Copilot cloud agent instead of this machine |
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 · 174 lines · 153 tokens per session scan A 8192cda8e49b
phoenix-mission is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 7d ago), licensed MIT. It adds 153 tokens to every session and 2,241 once invoked, about $0.0008 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…