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 instructions/serpbase-dev/serpbase-skill/agents-mdgit clone --depth 1 https://github.com/serpbase-dev/serpbase-skillWhat 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 | $0.00495 | $0.00495 |
| Opus 5 | $0.00247 | $0.00247 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
serpbase-skill AGENTS.md 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 yesterday.
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
SerpBase Agent Instructions
Use this file for agents that read project-level instructions such as Codex, opencode, OpenClaw-style agents, and other coding/research agents.
Capability
Use SerpBase for current Google SERP data:
- Google Search: web results and SERP modules
- Google Images: image URLs, thumbnails, and source pages
- Google News: articles, publishers, timestamps, and snippets
- Google Videos: video links, sources, durations, and thumbnails
- Google Maps Search: local places
- Google Maps Detail: place detail by
feature_id
Authentication
Require SERPBASE_API_KEY in the environment, or pass --api-key to scripts/serpbase_search.py.
Never print, log, commit, or reveal API keys. If the key is missing, ask the user to create one at https://serpbase.dev/dashboard/api-keys.
How To Call
Prefer a SerpBase MCP server if one is available. Otherwise run the bundled script from this folder:
python scripts/serpbase_search.py --type search --query "python asyncio" --hl en --gl us --page 1
Maps search:
python scripts/serpbase_search.py --type maps_search --query "coffee" --lat 37.7749 --lng -122.4194 --zoom 14
Maps detail:
python scripts/serpbase_search.py --type maps_detail --feature-id "0x8085809c2c6fdc63:0x4b3f2d70e4f5a123"
Routing
- Broad web discovery:
search - Images:
images - News/current publisher discovery:
news - Videos/tutorial/media discovery:
videos - Local businesses or places:
maps_search - Details for one Maps result:
maps_detail
Use hl=en, gl=us, page=1 unless the task or user explicitly calls for another locale. For Maps geo-targeting, send lat and lng together.
Answering
Cite result URLs where available. Use link, url, display_url, or google_maps_url as source fields. Separate facts returned by SerpBase from your inference. Do not invent missing fields.
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.
- yesterday First seen · 56 lines · 495 tokens per session scan A 6fca6cbf1701
serpbase-skill AGENTS.md is an instructions file published in the GitHub repository serpbase-dev/serpbase-skill (2 stars, last pushed 3mo ago), licensed MIT. It adds 495 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
ai-text-detector AGENTS.md
Instructions for lynote-ai/ai-text-detector, covering agent instructions: ai detector skill, when to use, required behavior, how to run and response format for users.
crossframe-skill AGENTS.md
Instructions for xi-kari/crossframe-skill, covering crossframe / agent adapter, 仓库怎么理解, 显式调用边界, 显式调用 crossframe essay and 显式调用其它平行 skill.
crossframe-skill copilot-instructions.md
Instructions for xi-kari/crossframe-skill, a project described as: CrossFrame Skill Suite：面向 AI agent 的中文结构诊断、公共议题分析、组织复盘、历史材料处理、追问和成文工作流；旗舰 CrossFrame ProMax 提供 v8-only、精确点名、可对账可修复的独立结构推演 runtime。.
crossframe-skill CLAUDE.md
Instructions for xi-kari/crossframe-skill, a project described as: CrossFrame Skill Suite：面向 AI agent 的中文结构诊断、公共议题分析、组织复盘、历史材料处理、追问和成文工作流；旗舰 CrossFrame ProMax 提供 v8-only、精确点名、可对账可修复的独立结构推演 runtime。.
crossframe-skill GEMINI.md
Instructions for xi-kari/crossframe-skill, a project described as: CrossFrame Skill Suite：面向 AI agent 的中文结构诊断、公共议题分析、组织复盘、历史材料处理、追问和成文工作流；旗舰 CrossFrame ProMax 提供 v8-only、精确点名、可对账可修复的独立结构推演 runtime。.
mcp-steroid CLAUDE.md
Instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.