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/MarcosNahuel/antigravity-plugin-ccWrote 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/marcosnahuel/antigravity-plugin-cc/review)<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/review"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/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 5.1 | $0.00024 | $0.00595 |
| Opus 5 | $0.00012 | $0.00298 |
| Sonnet 5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
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 8d 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.
What it actually says
Route this to the antigravity:agy-rescue subagent in MODE: review.
Raw user request: $ARGUMENTS
Routing rules:
-
If the request contains
--background, invoke the subagent withrun_in_background: true. Strip the flag. -
Capture the current git diff BEFORE delegating. Use ONE Bash call with this exact fallback chain (do not invent your own —
git diff HEADfirst because it includes committed-but-not-pushed work too):set -e REPO_DIR="${CLAUDE_PROJECT_DIR:-$PWD}" DIFF_FILE="$(mktemp -t agy-review-XXXXXX.diff 2>/dev/null || mktemp)" git -C "$REPO_DIR" diff HEAD > "$DIFF_FILE" 2>/dev/null || true if [ ! -s "$DIFF_FILE" ]; then git -C "$REPO_DIR" diff > "$DIFF_FILE" 2>/dev/null || true fi if [ ! -s "$DIFF_FILE" ]; then rm -f "$DIFF_FILE" echo "NO_DIFF" else OUT_FILE="${DIFF_FILE%.diff}.review.md" echo "DIFF_FILE=$DIFF_FILE" echo "OUT_FILE=$OUT_FILE" wc -l < "$DIFF_FILE" fi -
If the Bash output is
NO_DIFF, tell the user "no git diff found in this repo — stage or make changes first" and stop. Do NOT invoke the subagent. -
Anything left in the user text after stripping
--backgroundis the focus text (may be empty). Default focus if empty: "review for correctness, edge cases, security issues, and style".
Pass this header block to the subagent followed by the focus text:
MODE: review
INTENSITY:
MODEL:
RESUME: false
WRITE_FILE: <absolute OUT_FILE path echoed above>
FOCUS: <focus text or default>
DIFF_FILE: <absolute path captured above>
USER_TEXT:
Operating rules:
- The subagent reads
DIFF_FILE, builds a review prompt embedding the diff + focus, invokes agy via the write_file workaround (bug #76), and returns the review verbatim. - Present agy's response as-is. No paraphrase.
- If agy reports missing/unauthenticated, tell the user to run
/agy:setup. - After delegating, leave the temp
DIFF_FILEalone — the subagent owns its lifecycle (it cleans up on success).
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.
- 8d ago First seen · 59 lines · 24 tokens per session scan A d900fe168fff
review is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (27 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 595 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
agy-review
Send the current change set to Antigravity (agy) for a senior-reviewer code review.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
audit-project
Multi-agent code review with iterative improvement.
check
A combined code-quality review and design-to-implementation consistency check. It reads the changed files once, then evaluates them from both review perspectives.
pr-review
Reviews pull request changes to provide feedback, check for issues, and suggest improvements before merging into the main codebase.
code-review
Perform a comprehensive code review of recent changes.