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-shipgit 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-ship)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-ship"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-ship/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-ship"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-ship.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 | $0.00084 | $0.00936 |
| Opus 5.5 | $0.00034 | $0.00374 |
| Sonnet 5.5 | $0.00017 | $0.00187 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
phoenix-ship 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-ship — declare done only on green evidence
Overview
This is the last line of defense against shipping silently-broken work. "Done" is not a feeling or a
diff that looks right — it is a green phoenix_sense on the acceptance check plus an intact trace that
proves the green is real. Phoenix exists to prevent exactly one failure: an agent confidently saying
"done" on work that doesn't actually work. This skill is where that promise is kept.
When to use
- The final step of any task, right before you tell the user it's complete or merge.
- Whenever you're about to type "done", "fixed", "ready", or "shipped".
The ship gate
About to say "done"
│
▼
1. phoenix_sense(acceptance_check) ──► must be ok:true
│ │ red?
▼ ▼
2. phoenix_verify_trace ──► STOP. Not done. → phoenix-debug
│ ok + intact chain?
▼
3. Report WITH evidence (check + trace head hash)
│
▼
DONE (provably)
1. Final acceptance sense
phoenix_sense(acceptance_check) from the Intent Contract (phoenix-think). Green is mandatory. Not
"the test I added" — the acceptance check that represents the user's actual definition of success.
2. Verify the trace
phoenix_verify_trace → ok:true with an intact hash chain. This proves the green you're about to
report is genuine and wasn't reached by skipping or editing a gate. A broken chain means you are not
done, no matter how the code looks.
3. Report with the evidence attached
State the check that passed and the trace head hash, so the claim is auditable:
"Done —
pytest -qexits 0 (acceptance check); trace verified, 14 rows, head9885e6df…."
That one line is the difference between a trustworthy completion and a hopeful one.
The rule that is the whole point
Never type "done" without a green phoenix_sense. If the check is red or the trace is broken, you
are not done — say exactly what is failing and route to phoenix-debug. "I'm not sure it passed" is an
acceptable, honest status; a fabricated completion is the cardinal failure this entire harness exists to
prevent.
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.
- 1mo ago First seen · 77 lines · 84 tokens per session scan A 4c9e37a34dd3
phoenix-ship is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (6 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 936 once invoked, about $0.0003 per session on Opus 5.5. 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
ai-agents-empirical-probe-toolkit
Prove-it methods for this repo. Six recipes for runtime-contract probes, guard and threshold calibration, eval A/B, docs-vs-reality audits, reproduce-on-main CI triage, and negative-control test design, each with a worked example from repo history. Use when you say probe the runtime contract, calibrate this guard…
ai-agents-portability-campaign
Execute cross-harness hook changes for Claude Code and GitHub Copilot CLI using the settled official contract, versioned probes, generators, and runtime tests. Use for run the portability campaign, port hooks to a new harness, copilot hook timeout regression, or new copilot cli release, recheck the contract. Do NOT…
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
repository-consumer-proof
Verify ai-agents hooks, installed dispatch, and behavior beyond green builds. Do NOT use for PR blockers (use repository-pr-recovery).
apex-terraform-test
WORKFLOW SKILL — Write and run Terraform tests (.tftest.hcl). WHEN: "create terraform test", "write tftest", ".tftest.hcl", "mock provider", "test module", "test assertion". USE FOR: test files, run blocks, assertions, mock providers, plan-mode unit tests, apply-mode integration tests, test troubleshooting. DO NOT USE…
pr-quality-qa
Judge a local diff on test coverage, error handling, and whether the tests would fail if the code regressed, and return a PASS/WARN/CRITICALFAIL verdict. Use when you say qa review my changes, run the qa gate, or are these tests good enough. Do NOT use to run all six axes (use pr-quality-all), and do NOT use to write…