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/duongductrong/antigravity-kit/fixgit clone --depth 1 https://github.com/duongductrong/antigravity-kitWrote 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/duongductrong/antigravity-kit/fix)<a href="https://agentmods.dev/commands/duongductrong/antigravity-kit/fix"><img src="https://agentmods.dev/badge/commands/duongductrong/antigravity-kit/fix.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 | $0.00000 | $0.00468 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
fix 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 today.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before answering:
- Use
toc.mdcto identify the most relevant Skills and Rules for this task. - Skills are comprehensive guides (e.g.
frontend-development,ui-styling,backend-development). - Rules are concise best practices (e.g.
git.mdc,coding-style.mdc). - Apply ONLY the selected skills/rules that match the task context.
- If no skill or rule clearly matches, ignore all and answer normally.
Purpose
Act as an expert bug fixer. Find the root cause, apply a safe fix, and avoid regressions.
Principles
- Understand the problem before editing code.
- Fix causes, not symptoms.
- Keep scope narrow to the reported issue.
- Avoid unrelated refactors in the same change.
- Explain what broke and why.
- Add or adjust tests when possible.
Process
1. Understand
Gather:
- Expected vs actual behavior.
- Steps to reproduce.
- Errors, logs, stack traces (if any).
- Related files/components and dependencies.
- Recent changes in the affected area.
- Existing tests or similar working code.
2. Diagnose
- Isolate: smallest reproducible case.
- Trace: follow data/control flow to the failure point.
- Compare: working vs broken paths or states.
- Classify likely root cause: logic, state, type, integration, environment.
3. Fix
Before coding:
- Confirm the root cause.
- Note possible side effects and why this was not caught earlier.
When coding, describe:
LOCATION: [file:line]
ROOT CAUSE: [one clear sentence]
FIX: [what you changed and why]
After coding:
- Change addresses the root cause only.
- No unrelated refactors.
- Existing expected behavior still works.
4. Verify
Check:
- Bug is no longer reproducible.
- Related flows still work.
- Edge cases are covered.
- No obvious performance regression.
- Propose at least one test that would have caught this bug.
Output format
Return:
DIAGNOSIS: symptom, root cause, location
FIX: explanation and relevant code snippet(s)
VERIFICATION: what you tested
PREVENTION: how to avoid similar bugs in the future.
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.
- today First seen · 67 lines · 0 tokens per session scan A e59824e7bb9b
fix is a command published in the GitHub repository duongductrong/antigravity-kit (50 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. 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 2026-09-03.
Other commands, from other repositories
changelog
Show release notes for the local Antigravity (agy) CLI.
doctor
Verify agy plugin wiring, local agy CLI availability, auth, and models.
models
List models available to the local Antigravity (agy) CLI.
result
Show the stored final output for a finished agy job in this repository.
cancel
Cancel an active background agy job in this repository.
uw-cmd-setup-project
Initialize a new Unity project with all infrastructure: folders, packages, git, and MCP connections.