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 agentmods add commands/ysicing/code-pilot/search-geminigit clone --depth 1 https://github.com/ysicing/code-pilotWhat 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 | $0.00011 | $0.00518 |
| Opus 5 | $0.00005 | $0.00259 |
| Sonnet 5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
search-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 2d 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.
What it actually says
Gemini 网络搜索
使用 Gemini CLI 执行网络搜索以获取最新信息。
使用方法
# 通过 Gemini CLI 进行网络搜索（必须）
gemini --prompt "WebSearch: <搜索查询>"
基本示例
# 使用 Gemini CLI
gemini --prompt "WebSearch: Debian13 新特性"
gemini --prompt "WebSearch: ysicing的博客地址是多少"
与 Claude 配合
# 文档搜索和摘要
gemini --prompt "WebSearch: Debian13 新特性"
「请总结搜索结果并说明主要功能」
# 错误调查
cat error.log
gemini --prompt "WebSearch: [错误消息] 解决方法"
「请从搜索结果中提出最合适的解决方法」
# 技术比较
gemini --prompt "WebSearch: Rust vs Go performance benchmark 2025"
「请从搜索结果总结性能差异」
详细示例
# 从多个来源收集信息
gemini --prompt "WebSearch: GraphQL best practices 2024 multiple sources"
「请从搜索结果整理多个可靠来源的信息」
# 调查时间序列变化
gemini --prompt "WebSearch: JavaScript ES2015 ES2016 ES2017 ES2018 ES2019 ES2020 ES2021 ES2022 ES2023 ES2024 features"
「请按时间顺序整理各版本的主要变更」
# 限定特定域名搜索
gemini --prompt "WebSearch: site:github.com Rust WebAssembly projects stars:>1000"
「请按星标数量从高到低列出 10 个项目」
# 最新的安全信息
gemini --prompt "WebSearch: CVE-2024 Node.js vulnerabilities"
「请总结发现的漏洞影响和对策」
禁止事项
- 禁止使用 Claude 的内置 WebSearch 工具
- 需要网络搜索时，必须使用
gemini --prompt "WebSearch: ..."
注意事项
- 如果 Gemini CLI 可用，必须使用
gemini --prompt "WebSearch: ..." - 网络搜索结果不一定总是最新的
- 重要信息建议通过官方文档或可靠来源确认
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.
- 2d ago First seen · 72 lines · 11 tokens per session scan A 1eb58a66bb05
search-gemini is a command published in the GitHub repository ysicing/code-pilot (38 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 518 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 commands, from other repositories
specify
Create or update the feature specification from a natural language feature description.
speckit.git.validate
Validate current branch follows feature branch naming conventions.
pr-address
Address PR review comments on current branch.
plan-save
Save the current session's plan to GitHub as an issue.
enforce_standards
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
OPSX: Sync
Sync delta specs from a change to main specs.