Antigravity Skill Vault is a collection of reusable Agent Skills for Google Antigravity, covering software development, operations, security, and business work. It is for people who want Antigravity agents to follow specialized expertise, personas, and structured workflows. The catalogue skills are entries from this collection.
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 rmyndharis/antigravity-skills --skill conductor-revertgit clone --depth 1 https://github.com/rmyndharis/antigravity-skillsWrote 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/rmyndharis/antigravity-skills/conductor-revert)<a href="https://agentmods.dev/skills/rmyndharis/antigravity-skills/conductor-revert"><img src="https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/conductor-revert/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/rmyndharis/antigravity-skills/conductor-revert"><img src="https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/conductor-revert.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 306 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.
- high Tool Misuse · line 305 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.
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 | $0.00020 | $0.02167 |
| Opus 5 | $0.00010 | $0.01084 |
| Sonnet 5 | $0.00004 | $0.00433 |
| Haiku 4.5 | $0.00002 | $0.00217 |
Grade A, and why
conductor-revert 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- conductor-revert — 97% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revert Track
Revert changes by logical work unit with full git awareness. Supports reverting entire tracks, specific phases, or individual tasks.
Use this skill when
- Working on revert track tasks or workflows
- Needing guidance, best practices, or checklists for revert track
Do not use this skill when
- The task is unrelated to revert track
- You need a different domain or tool outside this scope
Instructions
- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
Pre-flight Checks
-
Verify Conductor is initialized:
- Check
conductor/tracks.mdexists - If missing: Display error and suggest running
/conductor:setupfirst
- Check
-
Verify git repository:
-
Run
git statusto confirm git repo -
Check for uncommitted changes
-
If uncommitted changes exist:
WARNING: Uncommitted changes detected Files with changes: {list of files} Options: 1. Stash changes and continue 2. Commit changes first 3. Cancel revert
-
-
Verify git is clean enough to revert:
- No merge in progress
- No rebase in progress
- If issues found: Halt and explain resolution steps
Target Selection
If argument provided:
Parse the argument format:
Full track: {trackId}
- Example:
auth_20250115 - Reverts all commits for the entire track
Specific phase: {trackId}:phase{N}
- Example:
auth_20250115:phase2 - Reverts commits for phase N and all subsequent phases
Specific task: {trackId}:task{X.Y}
- Example:
auth_20250115:task2.3 - Reverts commits for task X.Y only
If no argument:
Display guided selection menu:
What would you like to revert?
Currently In Progress:
1. [~] Task 2.3 in dashboard_20250112 (most recent)
Recently Completed:
2. [x] Task 2.2 in dashboard_20250112 (1 hour ago)
3. [x] Phase 1 in dashboard_20250112 (3 hours ago)
4. [x] Full track: auth_20250115 (yesterday)
Options:
5. Enter specific reference (track:phase or track:task)
6. Cancel
Select option:
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 · 372 lines · 20 tokens per session scan A 2cf3f1761fe9
conductor-revert is a skill published in the GitHub repository rmyndharis/antigravity-skills (1,529 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,167 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 skills, from other repositories
github
Manages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way. Automatically runs the code-review skill before any commit. Enforces Conventional Commits standard. Handles the full lifecycle: branch → review → commit → push → PR.
changelog
Generates and maintains changelogs following Keep a Changelog format. Use when updating release notes, finishing tasks, or tagging versions. For version bumps, see semantic-versioning.
conventional-commits
Enforces Conventional Commits format for git commit messages. Use when formatting commits or validating message structures. For git commands, see git-control.
git-control
Standardizes git operations, branch management, and disaster recovery. Use when committing, branching, or resolving conflicts. For commit formatting, see conventional-commits.
semantic-versioning
Manages project versioning following Semantic Versioning (SemVer) principles. Calculates increments based on changes and synchronizes version across documentation and metadata. Use when the user asks to "bump the version", "prepare a release", or when the changelog skill calls for a release.
ios-appstore-builder
Prepare, configure, and publish iOS apps to the Apple App Store. Covers certificates, provisioning profiles, TestFlight, App Store submission, and review guidelines.