Gemini Delegation
- 107 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
Route agent work to Google Gemini CLI when delegation-core picks Gemini or you need roughly 1M-token context windows.
About
Gemini Delegation is an agent skill that connects Claude Night Market’s delegation-core to Google’s Gemini CLI so solo builders can offload subtasks to Gemini without rewriting their orchestration. It is for indie developers who already use multi-model setups and need a single, documented path when the router chooses Gemini or when a job exceeds what fits comfortably in a smaller window. The skill spells out model tiers, how to pipe files and directories into prompts with @path patterns, sandbox mode, and JSON output for scripted handoffs. It also covers practical ops: free-tier rate limits, trimming context with selective globs or comment stripping, and checking status via bundled hooks. Use it during Build when you are composing agent tooling stacks—not as a standalone product feature for end users.
- Documents gemini-2.5-flash-exp, gemini-2.5-pro-exp, and gemini-exp-1206 with context and use-case matrix
- CLI flags: -p prompt, --model, --output-format json, -s sandbox, and @path context inclusion
- Cost reference per 1M tokens (Flash vs Pro input/output)
- Troubleshooting for HTTP 429 rate limits, oversized context, and regional model availability
- Implements delegation-core for Google models when selected or when 1M+ context is required
Gemini Delegation by the numbers
- 107 all-time installs (skills.sh)
- Ranked #4,123 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill gemini-delegationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 107 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Route agent work to Google Gemini CLI when delegation-core picks Gemini or you need roughly 1M-token context windows.
Files
Table of Contents
Gemini CLI Delegation
Overview
This skill implements conjure:delegation-core for the Gemini CLI. It provides Gemini-specific authentication, quota management, and command construction.
For shared delegation patterns, see Skill(conjure:delegation-core).
When To Use
- After
Skill(conjure:delegation-core)determines Gemini is suitable - When you need Gemini's large context window (1M+ tokens)
- For batch processing, summarization, or pattern extraction tasks
- If the
geminiCLI is installed and authenticated
Prerequisites
Installation:
# Verify installation
gemini --version
# Check authentication
gemini auth status
# Login if needed
gemini auth login
# Or set API key
export GEMINI_API_KEY="your-key"Verification: Run the command with --help flag to verify availability.
Quick Start
Basic Command
# File analysis
gemini -p "@path/to/file Analyze this code"
# Multiple files
gemini -p "@src/**/*.py Summarize these files"
# With specific model
gemini --model gemini-2.5-pro-exp -p "..."
# JSON output
gemini --output-format json -p "..."Save Output
gemini -p "..." > delegations/gemini/$(date +%Y%m%d_%H%M%S).mdGemini-Specific Details
For Gemini-specific models, CLI options, cost reference, and troubleshooting, see modules/gemini-specifics.md.
Gemini-Specific Configuration
Model Reference
| Model | Use Case | Context |
|---|---|---|
gemini-2.5-flash-exp | Fast, simple tasks | Up to 1M tokens |
gemini-2.5-pro-exp | Complex analysis | Up to 1M tokens |
gemini-exp-1206 | Experimental features | Varies |
CLI Options
| Flag | Purpose |
|---|---|
-p "prompt" | Specify prompt |
--model <name> | Select model |
--output-format json | JSON output |
-s | Sandbox mode |
@path | Include file in context |
Context Inclusion Patterns
- Use
@pathto include file contents - Use
@directory/**/*for recursive inclusion - Gemini handles large contexts well (1M+ tokens)
Cost Reference (per 1M tokens)
- Input: $0.50 (Pro), $0.075 (Flash)
- Output: $1.50 (Pro), $0.30 (Flash)
Gemini-Specific Troubleshooting
Rate Limit (HTTP 429)
- Free tier: ~60 RPM, ~1000 requests/day
- Consider
gemini-2.5-flashto reduce RPM usage - Use
~/conjure/hooks/gemini/status.shfor quick check
Context Too Large
- Use selective globbing:
src/**/*.pyinstead ofsrc/**/* - Pre-process:
rg -v "^\s*#" file.pyto remove comments (orgrep -v)
Region Issues
- Some models available only in certain regions
- Check API documentation for availability
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
Is Gemini Delegation safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.