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-reviewgit 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-review)<a href="https://agentmods.dev/skills/all-the-vibes/atv-phoenix/phoenix-review"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-review/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-review"><img src="https://agentmods.dev/badge/skills/all-the-vibes/atv-phoenix/phoenix-review.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 | $0.00078 | $0.00909 |
| Opus 5 | $0.00039 | $0.00454 |
| Sonnet 5 | $0.00016 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
phoenix-review 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phoenix-review — evidence-based review, not vibes
Overview
Before anything ships, prove it meets the intent — objectively. A Phoenix review is not a re-read of the diff hoping to spot problems; it re-runs the checks, confirms nothing else regressed, and inspects the trace to confirm the green you see is real and was reached honestly. It surfaces correctness issues only — the model already handles style; Phoenix reviews whether the work actually works.
When to use
- A feature/step set is "done" and headed for
phoenix-ship. - Before merging or handing off.
- After a non-trivial
phoenix-buildorphoenix-debugsession.
The review gate
Completed work
│
▼
1. Re-run the ACCEPTANCE check (from phoenix-think) → must be green
│
▼
2. Re-run the FULL suite/build/lint → no regressions
│
▼
3. phoenix_verify_trace → chain intact, real green→work→green
│
▼
4. Surface ONLY real issues (bugs / unmet criteria / regressions)
│
▼
green evidence ─► phoenix-ship any red / broken trace ─► phoenix-debug
1. Re-run the acceptance gate
phoenix_sense(acceptance_check) from the Intent Contract. If it isn't green, the work is not
review-passed — full stop. Send it back to phoenix-build/phoenix-debug.
2. Check for regressions
Sense the full suite/build/lint, not just the new test. The most common review miss is a change
that satisfies its own check while breaking something adjacent. Use phoenix-context impact to
confirm you tested everything in the blast radius.
3. Inspect the trace
phoenix_verify_trace must report ok:true with an intact hash chain showing a genuine
green→(work)→green path. A broken chain, or a "green" with no prior red, means the gate was skipped or
the evidence was edited — treat that as a failed review.
4. Surface only what matters
Raise: unmet acceptance criteria, bugs, regressions, security/correctness risks, missing error handling on a real failure path. Do not raise style, naming taste, or formatting nits — that's noise, and the model handles it already. High signal-to-noise is the whole value of the review.
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 · 78 lines · 78 tokens per session scan A 6e25b9c4a387
phoenix-review is a skill published in the GitHub repository All-The-Vibes/ATV-Phoenix (5 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 909 once invoked, about $0.0004 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
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.
parity-guard-test-pattern
When checking that all callers of a contract implement it correctly, you get false positives from wrapper delegators.
source-coding-discipline
Use when a task involves reading, editing, reviewing, testing, debugging, refactoring, or otherwise working with source code files. Source paths include /.{py,ts,tsx,js,jsx,mjs,go,rs,java,kt,swift,rb,c,cc,cpp,h,hpp,sh,bash,zsh,sql,vue,svelte}. Do not use for docs-only, planning-only, or non-code file tasks unless the…
setup-pre-commit
Use when bootstrapping or extending the pre-commit hook chain (Husky + lint-staged + Prettier + typecheck + integration tests) for an EVOKORE-style TypeScript repo, including detecting an existing setup, surfacing the diff, and never silently overwriting a configured chain.
vibeflow-audit
Audits implementation against its DoD and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. With --consolidate-hotfixes, reclassifies hotfix trace docs against the…
loop-verifier
Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.