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 agentmods add commands/vorobiovd/air/reviewgit 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)<a href="https://agentmods.dev/commands/vorobiovd/air/review"><img src="https://agentmods.dev/badge/commands/vorobiovd/air/review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.30171 |
| Opus 5 | $0.00014 | $0.15085 |
| Sonnet 5 | $0.00006 | $0.06034 |
| Haiku 4.5 | $0.00003 | $0.03017 |
Grade D, and why
review scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
CODEX_SCRIPT=$(find ~/.claude/plugins/cache/openai-codex -name "codex-companion.mjs" 2>/dev/null | sort -V | tail -1) Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find /tmp -maxdepth 1 -name 'air-*' -mtime +1 -exec rm -rf {} + 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 1,374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review code using specialized agents. If a PR number is given, review that PR. If no arguments, auto-detect: review the current branch's PR if one exists, or self-review local changes if not.
Setup
air reviews GitHub PRs via the gh CLI (must be authenticated — gh auth login).
PLATFORM_DOMAIN builds the wiki + finding-link URLs below — derive it from the
remote host so GitHub Enterprise (and SSH remotes) work, defaulting to github.com:
REMOTE_URL=$(git remote get-url origin 2>/dev/null)
if [[ "$REMOTE_URL" =~ ^https?://([^/]+)/ ]]; then
PLATFORM_DOMAIN="${BASH_REMATCH[1]}"
elif [[ "$REMOTE_URL" =~ ^git@([^:]+): ]]; then
PLATFORM_DOMAIN="${BASH_REMATCH[1]}"
else
PLATFORM_DOMAIN="github.com"
fi
Step 0: Initialize Session Temp Directory
Before any /tmp write, mint a per-invocation session dir. Claude Code's Bash tool starts a fresh shell per call, so export doesn't persist — capture the literal path from the command below and interpolate it into every subsequent $AIR_TMP reference in this file. Also sweep stale dirs from crashed prior runs.
# GC old session dirs (>1 day) from crashed prior runs
find /tmp -maxdepth 1 -name 'air-*' -mtime +1 -exec rm -rf {} + 2>/dev/null
# Mint the session dir. `mktemp -d` guarantees a non-empty, non-colliding path.
AIR_TMP=$(mktemp -d "/tmp/air-XXXXXX")
# Repo root (used by Step 3.5 when writing `.air-checks.sh` — same-repo only).
# Falls back to empty when invoked from outside a git repo; Step 3.5 skips
# `.air-checks.sh` generation in that case.
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null)
# Plugin root (used by Step 13's meta.py invocations and hooks).
# The pre-commit hook exports this for .air-checks.sh; review.md has to
# derive it independently since Claude Code doesn't pass it to slash
# commands. We resolve it via the canonical cache path; if the user has
# the plugin installed elsewhere, they can set AIR_PLUGIN_ROOT manually.
if [ -z "${AIR_PLUGIN_ROOT:-}" ]; then
AIR_PLUGIN_ROOT=$(ls -1d ~/.claude/plugins/cache/air/air/*/ 2>/dev/null | sort -V | tail -1 | sed 's:/$::')
fi
if [ -z "$AIR_PLUGIN_ROOT" ] || [ ! -d "$AIR_PLUGIN_ROOT" ]; then
echo "warning: AIR_PLUGIN_ROOT not resolvable; Step 13's auto-trigger counter will not increment this run" >&2
AIR_PLUGIN_ROOT=""
fi
echo "$AIR_TMP"
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.
- 5d ago First seen · 1,374 lines · 0 tokens per session scan D 3155a43e8be6
review is a command published in the GitHub repository VorobiovD/air (5 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 30,171 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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
Review PRs against the conventions learned from each repo — 1 post per PR, findings tagged by severity, code left untouched.
release-now
Create a git tag + GitHub Release for open-pr — an official release if standing on main, an RC if standing on a branch with an open PR (a dev tool specific to this repo, not shipped in the plugin).
fix
Act on the findings a review left on a PR — takes or declines each by severity, edits code at pwd to match the project, 1 commit, replies once pushed.
feedback
Report a problem with the open-pr plugin itself, or ask for a change, on its public issue tracker. Reads no PR; writes nothing in your repo.
upgrade
Bring every per-repo config found below pwd up to the schema this build expects. Takes no PR.
smoke
Smoke-test the agent-smith CLI binary + docker-compose for api-scan / security-scan / fix-bug. Catches regressions that escape the unit test suite.