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 skills add J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill anti-gravitygit clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-SuiteWrote 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/skills/j-star-films-studios/vibecode-protocol-suite/anti-gravity)<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/anti-gravity"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/anti-gravity/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/skills/j-star-films-studios/vibecode-protocol-suite/anti-gravity"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/anti-gravity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 61 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00045 | $0.01077 |
| Opus 5 | $0.00023 | $0.00539 |
| Sonnet 5 | $0.00009 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
anti-gravity 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-Gravity Skill Guide
When to Use Anti-Gravity
- When the user asks for Gemini-like analysis, review, planning, design critique, or broad context work.
- When a second-model perspective is useful.
- When the task can be expressed as a short, direct
agyprompt.
Tested Behavior in This Harness
agy -p may produce an empty captured stdout inside the Pi/sandbox harness even when the model answered successfully. The reliable way to verify output here is:
- run
agy -pwith a short exact prompt, - capture a log with
--log-file, - read the created conversation id from the log,
- inspect
C:/Users/johno/.gemini/antigravity-cli/brain/<conversation-id>/.system_generated/logs/transcript.jsonlfor the final model response.
The CLI stores conversation state under:
C:/Users/johno/.gemini/antigravity-cli/
If the harness reports Access is denied while renaming files in conversations/, the response may still be present in the transcript. Prefer checking the transcript before retrying.
Core CLI Modes
agy -p "prompt"oragy --print "prompt"— run a single prompt and print/respond non-interactively.agy --prompt "prompt"— alias for print mode.agy -coragy --continue— continue the most recent conversation.agy --conversation <ID>— resume a previous conversation by ID.agy -i "prompt"oragy --prompt-interactive "prompt"— start interactively and continue the session.agy --sandbox— run with terminal restrictions enabled.
Workspace and Safety Flags
--add-dir <DIR>— add a directory to the workspace; repeat for multiple directories.--log-file <PATH>— write CLI logs to a known path for debugging and transcript discovery.--print-timeout <DURATION>— set print-mode wait time, e.g.60s,5m.--dangerously-skip-permissions— auto-approve tool permission requests. Use only when explicitly appropriate.
Prompting Rules
Anti-Gravity follows instructions better when prompts are short and strict.
Use this style:
Do not use tools. Return exactly AGY_OK and nothing else.
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.
- 12d ago First seen · 113 lines · 45 tokens per session scan A ac783c9d72e3
anti-gravity is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed yesterday), licensed ISC. It adds 45 tokens to every session and 1,077 once invoked, about $0.0002 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 skills, from other repositories
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
code-review
Perform comprehensive code reviews focusing on best practices, security vulnerabilities, performance optimization, and maintainability.
code-review
Reviews code for bugs, security issues, and best practices.
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
mcp-server-review
Review a Model Context Protocol (MCP) server implementation against the 2026-07-28 protocol revision, which removed the initialize handshake and Mcp-Session-Id and made the protocol stateless. Use when the user asks to review, audit, upgrade or migrate an MCP server, asks whether their MCP server is spec compliant…
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.