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.
git clone --depth 1 https://github.com/VorobiovD/airWrote 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/commands/vorobiovd/air/review-solo)<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.
<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>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 | $0.00000 | $0.01695 |
| Opus 5 | $0.00000 | $0.00847 |
| Sonnet 5 | $0.00000 | $0.00339 |
| Haiku 4.5 | $0.00000 | $0.00169 |
Grade B, and why
review-solo scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
CODEX_SCRIPT=$(find ~/.claude/plugins/cache/openai-codex -name "codex-companion.mjs" 2>/dev/null | sort -V | tail -1) 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).
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 · 123 lines · 0 tokens per session scan B 5a118a17e40b
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.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.