gemini-prompting

gemini-prompting is a skill for Claude Code from LovelaceLoom/gemini-plugin-cc. It costs 28 tokens per session (784 once invoked), scanned A, original, Apache-2.0.

Internal guidance for improving prompts sent to Gemini, Google's AI model, from a Claude Code plugin. It focuses on coding, code review, diagnosis, and research requests.

In plain words
What is it for?
Use it when preparing a Gemini request that needs broad repository context, code tracing, or analysis of logs and related files.
Why use it?
It helps turn a loosely worded rescue request into a focused prompt with a goal, context, constraints, and expected result. It is intended for use inside the plugin's Gemini rescue command.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

Part of the gemini plugin — 3 skills, 9 commands, 1 agent, 3 hooks shipped together

Good fit Use it when preparing a Gemini request that needs broad repository context, code tracing, or analysis of logs and related files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lovelaceloom/gemini-plugin-cc/gemini-prompting
Install

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.

Any agent
npx skills add LovelaceLoom/gemini-plugin-cc --skill gemini-prompting
Clone the repo
git clone --depth 1 https://github.com/LovelaceLoom/gemini-plugin-cc

Made for: Claude Code.

Or install gemini, the plugin that ships this one along with the rest of its 3 skills, 9 commands, 1 agent, 3 hooks.

Wrote 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.

agentmods badge for gemini-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/lovelaceloom/gemini-plugin-cc/gemini-prompting/github.svg)](https://agentmods.dev/skills/lovelaceloom/gemini-plugin-cc/gemini-prompting)
Your own site
<a href="https://agentmods.dev/skills/lovelaceloom/gemini-plugin-cc/gemini-prompting"><img src="https://agentmods.dev/badge/skills/lovelaceloom/gemini-plugin-cc/gemini-prompting/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.

agentmods 80×15 button for gemini-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/lovelaceloom/gemini-plugin-cc/gemini-prompting"><img src="https://agentmods.dev/badge/skills/lovelaceloom/gemini-plugin-cc/gemini-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00784
Opus 5 $0.00014 $0.00392
Sonnet 5 $0.00006 $0.00157
Haiku 4.5 $0.00003 $0.00078

Measured 10d ago against content hash bc20592c3b22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gemini-prompting 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 10d 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.

plugins/gemini/skills/gemini-prompting/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composing Gemini prompts

Use this skill from inside gemini:gemini-rescue (and only there) to tighten a user's free-form rescue request into a more effective Gemini prompt before calling task.

This skill draws on Gemini's distinct strengths:

  • Large context window (1M tokens) — Gemini can absorb whole subdirectories, traces, and long logs at once. Prefer giving it raw context over hand-summarized excerpts when the question depends on cross-file behavior.
  • Strong code analysis — Gemini is good at tracing data flow, finding inconsistencies across files, and spotting missing handlers.
  • Distinct reasoning style — Gemini tends to be direct and specific. Don't pad the prompt with Claude-style hedging.

Prompt structure

A good rescue prompt for Gemini is short, direct, and grounded:

  1. Goal — one sentence stating what the user wants resolved or answered.
  2. Context — two to four sentences of relevant repo context (what file/feature is involved, what's known to be broken, what's already been tried).
  3. Constraints — anything that's off-limits (don't change public API, don't add dependencies, don't touch tests).
  4. Output expectation — what Gemini should return: an explanation, a diagnosis, a patch plan, or actual code edits.

Patterns

User intent Prompt pattern
"investigate why X" Goal: diagnose root cause. Context: behavior + reproduction. Output: ranked list of suspect causes with evidence.
"fix the failing test" Goal: make <test name> pass. Context: test file + recent changes. Output: minimal patch + explanation.
"explain how X works" Goal: explain the data/control flow of <feature>. Output: a walkthrough citing files and line numbers.
"what should the design be" Goal: propose a design for <feature>. Output: 2–3 options with tradeoffs, then a recommendation.

Anti-patterns

  • Don't restate the entire repo. Gemini will pull what it needs.
  • Don't ask Gemini to "be careful" or "be thorough" — it already is.
  • Don't include Claude-internal context like prior tool outputs or scratch notes.
  • Don't pre-decide the fix. Let Gemini propose its own approach.

Read the full file on GitHub · 52 lines

Changes

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.

  1. 10d ago First seen · 52 lines · 28 tokens per session scan A bc20592c3b22

Subscribe to this mod's changes

gemini-prompting is a skill published in the GitHub repository LovelaceLoom/gemini-plugin-cc (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 784 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 2026-08-31.

Related

Other skills, from other repositories

nativeprompt

A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.

edvardgrishin27/nativeprompt · 147 tokens

prompt-tuning

Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.

jjanczur/tyran · 58 tokens

prompt-coach

A hook-driven coach that reads every prompt sent to Claude Code and rewrites it toward proven prompting habits — definition-of-done, scoped references, guardrails, verification. Rules graduate as they are demonstrated, so the coaching fades as the user improves. The hook runs on its own, but load this skill when the…

alexmond/alexmskills · 177 tokens

ccc-prompt-fix

Fix and sharpen a prompt. Diagnoses it against the 6 prompt-quality patterns, returns a tightened rewrite with the reasoning, and suggests the right library prompt for your task.

KevinZai/commander · 41 tokens

context-engineering

Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).

komluk/scaffolding · 62 tokens

engineer-prompts

Builds or audits testable prompt contracts with explicit outcomes, permissions, tools, evidence, and stop conditions. Use when writing reusable agent prompts, system prompts, or prompts with unclear success criteria.

Drizzy07x/Skillquiver · 44 tokens