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/wangke19/gemini-ai-helpersWrote 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/wangke19/gemini-ai-helpers/compare)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/compare"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/compare/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/commands/wangke19/gemini-ai-helpers/compare"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/compare.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00007 | $0.02234 |
| Opus 5 | $0.00003 | $0.01117 |
| Sonnet 5 | $0.00001 | $0.00447 |
| Haiku 4.5 | $0.00001 | $0.00223 |
Grade B, and why
compare scanned grade B with 1 finding 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- RHEL/Fedora: `sudo dnf install skopeo` How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
container-image:compare
Synopsis
/container-image:compare <image1> <image2>
Description
The container-image:compare command compares two container images and identifies their differences. This is useful for understanding what changed between image versions, comparing images from different registries, or verifying image rebuilds.
The command analyzes and compares:
- Image metadata (digests, creation dates)
- Layer differences (added, removed, modified)
- Size differences
- Configuration changes (environment variables, labels, entrypoints)
- Platform/architecture support
- Security and vulnerability differences (if scanning tools available)
This command is useful for:
- Understanding changes between image versions
- Verifying image rebuilds match expectations
- Comparing images across registries (e.g., production vs staging)
- Identifying what layers changed in an update
- Troubleshooting deployment issues
- Security auditing and change tracking
Prerequisites
Required Tools:
- skopeo - For image inspection and comparison
- Check if installed:
which skopeo - Installation:
- RHEL/Fedora:
sudo dnf install skopeo - Ubuntu/Debian:
sudo apt-get install skopeo - macOS:
brew install skopeo
- RHEL/Fedora:
- Documentation: https://github.com/containers/skopeo
- Check if installed:
Optional Tools:
-
podman - For additional image analysis
- Useful for layer-by-layer comparison
- Installation: See
/container-image:inspectprerequisites
-
dive - For detailed layer analysis
- Check if installed:
which dive - Installation: https://github.com/wagoodman/dive
- Provides interactive layer comparison
- Check if installed:
Registry Authentication:
For private registries:
skopeo login registry.example.com
Implementation
The command performs the following comparison:
-
Check Tool Availability:
- Verify
skopeois installed - Check for optional tools (
podman,dive)
- Verify
-
Inspect Both Images:
skopeo inspect docker://<image1> skopeo inspect docker://<image2>
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.
- 9d ago First seen · 290 lines · 7 tokens per session scan B b2c6890bcd9e
compare is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 2,234 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
start
Starts the Supabase local development stack.
stop
Stops the Supabase local development stack.
create-docker-mcp-tunnel
Stand up an Google MCP tunnel locally with Docker Compose so Gemini can call a private MCP server (manual-credentials quickstart).
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.
redteam
Find likely failure paths, abuse cases, and proportionate mitigations.
ocean-stop
Gracefully stop the boil-ocean run and its scheduler.