Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MarcosNahuel/antigravity-plugin-cc/plugin install antigravityWrote 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/notebook-audit)<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/notebook-audit"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/notebook-audit.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 | $0.00064 | $0.00553 |
| Opus 5 | $0.00032 | $0.00277 |
| Sonnet 5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
notebook-audit 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 7d 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
Run a deterministic, read-only consistency audit over the notebook.db that /agy:notebook
built. It surfaces the conflicts you must resolve before trusting a total or building a liquidation —
each one cited to its source document. No agy, no model — just SQL over the structured facts.
Raw user request: $ARGUMENTS
Phase 0 — Resolve + run (ONE Bash call)
Resolve OUTDIR = docs/agy/notebook/<slug> from the folder argument (same slug() the notebook
uses). If notebook.db is missing, tell the user to run /agy:notebook <folder> | <objetivo> first
and stop. Otherwise run the audit:
python "${CLAUDE_PLUGIN_ROOT:-$PWD}/plugins/antigravity/scripts/notebook_audit.py" "$OUTDIR"
It prints AUDIT findings=N report=…/CONTRADICCIONES.md and writes the report. Checks:
- A same concepto with conflicting
monto_centsacross documents, - B same person id under two or more different names,
- C same reference under two or more different values,
- D documents that failed processing (
estado='no_procesado') — coverage gaps, - E amounts that couldn't be parsed to cents (OCR review),
- F same organization under two or more different names.
Phase 1 — Present
Read <OUTDIR>/CONTRADICCIONES.md and present it. Lead with the count and the highest-stakes
findings (A and B — money and identity conflicts). For each, name the documents involved and advise
verifying against the original before acting. If findings=0, say the corpus is internally
consistent on these checks (note it does not prove correctness, only the absence of these conflicts).
Notes
- Read-only; never writes to the DB. Re-run after a fresh
/agy:notebookto re-audit. - This is a consistency check (contradictions within the corpus), not a grounding check — pair it
with
/agy:notebook-queryto verify a specific figure against its source.
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.
- 7d ago First seen · 44 lines · 0 tokens per session scan A d1371d4d3b3a
notebook-audit is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (27 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 553 once invoked, about $0.0003 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
generate
Generate structured Obsidian Markdown from existing OCR text (requires rawtext.json).
gemini-imagegen
Generate or edit an image via a Gemini (agy) session — Gemini's generateimage tool does what Claude cannot.
deep
A command for researching a topic from seven perspectives, including product strategy, user experience, technology, practice, academic work, history, and online discussion. It combines the findings into a web report, Markdown document, and Notion page.
agy-debug
Send an error/stack trace plus the relevant file(s) to Antigravity (agy) for root-cause analysis.
agy-review
Send the current change set to Antigravity (agy) for a senior-reviewer code review.
agy-panel
Ask Antigravity (agy) the same question across several distinct models and compare their answers side by side.