review-solo

review-solo is a command for Claude Code from VorobiovD/air. It costs 0 tokens per session (1,695 once invoked), scanned B, original, MIT.

A command that runs six code-review checks in one agent pass and then verifies the results. It can also run an independent Codex check and optionally add an approval or change-request decision.

In plain words
What is it for?
Use it for command-line pull-request reviews when you want a single-agent review, an independent cross-check, or an optional verdict gate.
Why use it?
It gives one review workflow for finding issues and checking those findings, while keeping the final decision optional by default.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

Part of the air plugin — 5 commands, 7 agents, 1 hook shipped together

Good fit Use it for command-line pull-request reviews when you want a single-agent review, an independent cross-check, or an optional verdict gate.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vorobiovd/air/review-solo
Install

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.

Clone the repo
git clone --depth 1 https://github.com/VorobiovD/air

Made for: Claude Code.

Or install air, the plugin that ships this one along with the rest of its 5 commands, 7 agents, 1 hook.

Wrote 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.

agentmods badge for review-solo

README.md
[![agentmods](https://agentmods.dev/badge/commands/vorobiovd/air/review-solo/github.svg)](https://agentmods.dev/commands/vorobiovd/air/review-solo)
Your own site
<a href="https://agentmods.dev/commands/vorobiovd/air/review-solo"><img src="https://agentmods.dev/badge/commands/vorobiovd/air/review-solo/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.

agentmods 80×15 button for review-solo

Your own site · 80×15
<a href="https://agentmods.dev/commands/vorobiovd/air/review-solo"><img src="https://agentmods.dev/badge/commands/vorobiovd/air/review-solo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,695 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01695
Opus 5 $0.00000 $0.00847
Sonnet 5 $0.00000 $0.00339
Haiku 4.5 $0.00000 $0.00169

Measured 10d ago against content hash 5a118a17e40b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

review-solo scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

CODEX_SCRIPT=$(find ~/.claude/plugins/cache/openai-codex -name "codex-companion.mjs" 2>/dev/null | sort -V | tail -1)
plugins/air/commands/review-solo.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solo Review Flow (--solo mode)

One agent applies all six review lenses + self-verifies in a single pass — the CLI counterpart of managed's AIR_REVIEW_MODE=solo, sharing the same assembled prompt (lib/solo_prompt.py) and the same verdict-gating contract (lib/verdict.py). Runs on Fable via your Claude Code subscription: ~3–7 min of agent time and $0 of Claude API spend. The Codex cross-check runs alongside it (an independent-vendor pass on the OpenAI API — a small cost) unless --no-codex: it catches what a single same-vendor agent can miss (a real incident: Codex caught a false positive the Claude passes confirmed).

Advisory by default; gate by opt-in. --solo posts the review comment WITHOUT an APPROVE/REQUEST_CHANGES verdict. --solo --gate opts into the full verdict path. Why: blocker-class validation (2026-06-12, n=10 replay) found Fable-solo's severity calibration is bimodal by finding type — it held 4/4 FUNCTIONAL blockers ("this will break / 403 / crash", including a fully blind one) but downgraded 0/4 DATA-EXPOSURE blockers (unscoped PII/secret/supply-chain exposure) to Medium, regardless of whether the finding was in its context. It FINDS the exposure issues (8/8 discovery, often deeper than production) — it just won't escalate them to a gating severity. On any codebase where data-exposure is the highest-severity class, that is the worst place to under-gate, so the verifier-anchored full pipeline stays the gating standard. Use --gate only where you accept that data-exposure findings may land as Mediums.

Scope (v1): fresh full-PR reviews only. No re-review delta tracking, no --rewrite. (Codex now runs as an external cross-check — see Solo Step 1.5; --no-codex skips it.) If Step 2 found an existing review and new commits, --solo still performs a full fresh review and posts a NEW comment (the footer SHA keeps future re-review detection working).

Entry conditions

Routed from review.md after Steps 0–5 completed: $AIR_TMP minted, context loaded (CLAUDE.md, wiki/store patterns), PR metadata + diff + commits fetched, blame/churn computed. $AIR_PLUGIN_ROOT resolved (Step 0).

Read the full file on GitHub · 123 lines

Changes

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.

  1. 10d ago First seen · 123 lines · 0 tokens per session scan B 5a118a17e40b

Subscribe to this mod's changes

review-solo is a command published in the GitHub repository VorobiovD/air (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,695 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.