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 ondrej-svec/heart-of-gold-toolkit --skill geminigit clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkitWrote 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/ondrej-svec/heart-of-gold-toolkit/gemini)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/gemini"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/gemini/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/ondrej-svec/heart-of-gold-toolkit/gemini"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 24 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.
- medium Excessive Agency · line 34 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 | $0.00034 | $0.01044 |
| Opus 5 | $0.00017 | $0.00522 |
| Sonnet 5 | $0.00007 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
gemini 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini CLI Skill Guide
Available Models
| Model | Best for |
|---|---|
gemini-3.1-pro |
Most capable — complex reasoning, agentic tasks, coding, long-context |
gemini-3-flash |
High-performance at lower cost, general-purpose |
gemini-3.1-flash-lite |
Fastest and cheapest — lightweight tasks, high-volume |
gemini-2.5-pro |
Advanced reasoning, deep coding (stable, well-tested) |
gemini-2.5-flash |
Best price-performance ratio, low-latency |
Default recommendation: gemini-3.1-pro for complex tasks, gemini-3-flash for speed.
Running a Task
- Ask the user (via
AskUserQuestion) which model to use (default:gemini-3.1-pro) AND which approval mode (default,auto_edit,yolo, orplan) in a single prompt with two questions. - Assemble the command:
-m, --model <MODEL>— the model to use--approval-mode <MODE>—default(prompt),auto_edit(auto-approve edits),yolo(auto-approve all),plan(read-only)-p, --prompt "<PROMPT>"— run in non-interactive (headless) mode-o text— text output format for clean parsing
- Run the command, capture output, and summarize the outcome for the user.
- After Gemini completes, inform the user: "You can resume this Gemini session at any time by saying 'gemini resume' or asking me to continue."
Quick Reference
| Use case | Approval mode | Key flags |
|---|---|---|
| Read-only review or analysis | plan |
--approval-mode plan -o text |
| Apply local edits (auto-approve edits) | auto_edit |
--approval-mode auto_edit -o text |
| Full auto (approve everything) | yolo |
-y -o text |
| Resume recent session | Inherited | -r latest -p "new prompt" -o text |
| Include extra directories | Match task needs | --include-directories <DIR> |
Following Up
- After every
geminicommand, immediately useAskUserQuestionto confirm next steps, collect clarifications, or decide whether to resume. - When resuming, use:
gemini -r latest -p "new prompt" -o text. The resumed session uses the same context from the original session. - Restate the chosen model and approval mode when proposing follow-up actions.
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 · 73 lines · 34 tokens per session scan A 3544df883ae8
gemini is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 34 tokens to every session and 1,044 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…