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 skills add Buzzmatic/awesome-agent-skills --skill brave-web-searchgit clone --depth 1 https://github.com/Buzzmatic/awesome-agent-skillsWrote 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.
[](https://agentmods.dev/skills/buzzmatic/awesome-agent-skills/brave-web-search)<a href="https://agentmods.dev/skills/buzzmatic/awesome-agent-skills/brave-web-search"><img src="https://agentmods.dev/badge/skills/buzzmatic/awesome-agent-skills/brave-web-search/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.
<a href="https://agentmods.dev/skills/buzzmatic/awesome-agent-skills/brave-web-search"><img src="https://agentmods.dev/badge/skills/buzzmatic/awesome-agent-skills/brave-web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01518 |
| Opus 5.5 | $0.00037 | $0.00607 |
| Sonnet 5.5 | $0.00019 | $0.00304 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
brave-web-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brave Web Search
Wraps the Brave Web Search endpoint (/res/v1/web/search). Returns ranked search results with rich structured data.
Auth via BRAVE_SEARCH_API_KEY (Search plan). Subscribe at https://api-dashboard.search.brave.com/app/subscriptions/subscribe.
Quick Start
Single query:
python skills/brave-web-search/scripts/search.py \
--query "rust programming tutorials" \
--output output/brave_web.json
With filters:
python skills/brave-web-search/scripts/search.py \
--query "site:moz.com schema markup" \
--country DE --search-lang de \
--count 20 --freshness pm \
--safesearch moderate \
--output results.json
Goggles re-ranking (allow-list):
python skills/brave-web-search/scripts/search.py \
--query "react hooks best practices" \
--goggles '$discard
$site=react.dev
$site=developer.mozilla.org' \
--output results.json
Parameters
| Flag | Maps to | Notes |
|---|---|---|
--query / -q |
q |
Required. 1-400 chars, max 50 words. |
--country |
country |
2-letter code or ALL. Default US. |
--search-lang |
search_lang |
Language code (en, de, ...). Default en. |
--ui-lang |
ui_lang |
UI locale (en-US). |
--count |
count |
1-20. Default 20. |
--offset |
offset |
0-9 for pagination. |
--safesearch |
safesearch |
off / moderate (default) / strict. |
--freshness |
freshness |
pd / pw / pm / py or YYYY-MM-DDtoYYYY-MM-DD. |
--result-filter |
result_filter |
Comma-separated: web,videos,news,discussions,faq,infobox,locations. |
--goggles |
goggles |
URL to a hosted Goggle, or inline rules (newline-separated). |
--extra-snippets |
extra_snippets |
true to add up to 5 extra snippets per result. |
--no-spellcheck |
spellcheck=false |
Disable auto-correct. |
--no-operators |
operators=false |
Disable search operators. |
--units |
units |
metric / imperial. |
--enable-rich-callback |
enable_rich_callback |
Returns rich.hint.callback_key for stocks/weather/sports/etc. |
--include-fetch-metadata |
include_fetch_metadata |
Adds fetched_content_timestamp to each result. |
--loc-lat / --loc-long |
X-Loc-Lat / X-Loc-Long |
Coordinates take priority for location-aware results. |
--loc-city / --loc-state / --loc-country / --loc-postal |
X-Loc-* headers |
Used only if no coordinates. |
--rich-callback-key |
n/a | Fetch rich enrichment data (/res/v1/web/rich) using callback key from a previous response. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 113 lines · 93 tokens per session scan A 3e82cbcde0ed
brave-web-search is a skill published in the GitHub repository Buzzmatic/awesome-agent-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 1,518 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.