brave-search-skills: Instructions file for Codex

AGENTS.md

brave-search-skills AGENTS.md is an instructions file for Codex, OpenCode from brave/brave-search-skills. It costs 789 tokens per session, scanned A, original, MIT.

A set of instructions for using Brave Search API skills, which let an agent search the web and retrieve information for answers or research. It includes web, image, local-place, and AI-answer search options.

In plain words
What is it for?
Use it to search the web, research topics, find images or places, retrieve pages for AI context, and produce cited answers.
Why use it?
It helps an agent choose the appropriate search method for web research, fact checking, images, locations, or information grounded in retrieved sources.

Instructions file for CodexOpenCode ✓ vendor

Written for Codex and OpenCode: the file is AGENTS.md.

This is brave/brave-search-skills's own configuration. It tells Codex and OpenCode how to work on brave-search-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything brave-search-skills configures →

About the project

Brave Search API Skills is a collection of agent skills that gives AI coding agents access to the Brave Search API. It is intended for agents such as Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, and other tools supporting the Agent Skills standard. The catalogue add-ons are the project's own skills and configuration guidance for using Brave Search.

brave/brave-search-skills · 175 stars · on GitHub · api.search.brave.com

Reuse

Borrowing it

Nothing to install: this file belongs to brave/brave-search-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brave/brave-search-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/brave/brave-search-skills

Made for: Codex, OpenCode.

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 brave-search-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brave/brave-search-skills/agents-md/github.svg)](https://agentmods.dev/instructions/brave/brave-search-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/brave/brave-search-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/brave/brave-search-skills/agents-md/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 brave-search-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/brave/brave-search-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/brave/brave-search-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 789 This file is loaded in full into every session.
When invoked 789 The same file — it is already loaded in full.
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 $0.00789 $0.00789
Opus 5 $0.00394 $0.00394
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 13d ago against content hash d454f8ea9282, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

brave-search-skills 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 13d 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.

AGENTS.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brave Search API Skills

This file enables AI agents to discover and use Brave Search API skills.

Skill Description
answers USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-search). Streaming/blocking. Citations.
bx USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking
images-search USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.
llm-context USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.
local-descriptions USE FOR getting AI-generated POI text descriptions. Requires POI IDs from local-place-search, or from web-search with result_filter=locations. Returns markdown descriptions grounded in web search context. Max 20 IDs per request.
local-place-search USE FOR finding places in the physical world - businesses, POIs, street addresses, cities and streets. Results carry address, coordinates, rating, opening hours and phone, so basic details need no follow-up call. Standalone - no POI IDs or prior web search required; the IDs it returns work with local-pois and local-descriptions. Locate by coordinates or a location string, or omit both to search globally. Omit the query to browse an area. Max 100 results.
local-pois USE FOR getting local business/POI details. Requires POI IDs from local-place-search, or from web-search with result_filter=locations. Returns full business information including ratings, hours, contact info. Max 20 IDs.
news-search USE FOR news search. Returns news articles with title, URL, description, age, thumbnail, profile. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.
spellcheck USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use this only for pre-search query cleanup or "Did you mean?" UI.
suggest USE FOR query autocomplete/suggestions. Fast (<100ms). Returns suggested queries as user types. Supports rich suggestions with entity info. Typo-resilient.
videos-search USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination.
web-search USE FOR web search. Returns ranked results with snippets, URLs, thumbnails. Supports freshness filters, SafeSearch, Goggles for custom ranking, pagination. Primary search endpoint.

Read the full file on GitHub · 29 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. 13d ago First seen · 29 lines · 789 tokens per session scan A d454f8ea9282

Subscribe to this mod's changes

brave-search-skills AGENTS.md is an instructions file published in the GitHub repository brave/brave-search-skills (175 stars, last pushed 2d ago), licensed MIT. It adds 789 tokens to every session, about $0.0039 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens