Agent skill

Duckduckgo Search

Free web search via DuckDuckGo - no API key needed. An agent skill from AlexAI-MCP/hermes-CCC.

MITAuto-check passedProductivity & Automation

Install Duckduckgo Search

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC duckduckgo-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/duckduckgo-search .claude/skills/duckduckgo-search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "duckduckgo-search" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search into .claude/skills/duckduckgo-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "duckduckgo-search", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC duckduckgo-search --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/duckduckgo-search .agents/skills/duckduckgo-search && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "duckduckgo-search" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search into .agents/skills/duckduckgo-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "duckduckgo-search", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC duckduckgo-search --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/duckduckgo-search .cursor/skills/duckduckgo-search && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "duckduckgo-search" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search into .cursor/skills/duckduckgo-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "duckduckgo-search", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/AlexAI-MCP/hermes-CCC.git --path skills/duckduckgo-search

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC duckduckgo-search --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/duckduckgo-search .gemini/skills/duckduckgo-search && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "duckduckgo-search" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search into .gemini/skills/duckduckgo-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "duckduckgo-search", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC duckduckgo-search

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/duckduckgo-search .github/skills/duckduckgo-search && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "duckduckgo-search" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search into .github/skills/duckduckgo-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "duckduckgo-search", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC duckduckgo-search --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/duckduckgo-search .opencode/skills/duckduckgo-search && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "duckduckgo-search" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/duckduckgo-search into .opencode/skills/duckduckgo-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "duckduckgo-search", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: duckduckgo-search
GitHub stars: 135
Token cost: ~1.6k tokens
SKILL.md length: 622 words
Files: 1
Skills in repo: 44
Repo updated: Apr 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Free web search via DuckDuckGo - no API key needed. An agent skill from AlexAI-MCP/hermes-CCC.

Works in 5 steps: Run a text search for broad discovery. → Switch to news search for recent… → Use images when you need visual… → …
Tasks that involve Web search
SKILL.md covers Purpose, Install, Why Use It and Python API, plus 14 more sections
Calls pip

What it does

Duckduckgo Search is an agent skill from AlexAI-MCP/hermes-CCC. Free web search via DuckDuckGo - no API key needed. Text, news, images. Use as fallback when other search tools unavailable.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Web search. It works with Python. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

When your agent uses it

Tasks that involve Web search

Example prompts

“/duckduckgo-search”

Requirements

Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Run a text search for broad discovery.
Switch to news search for recent developments.
Use images when you need visual references or diagrams.
Save URLs and summarize locally.
Re-run with a region or time filter when result quality is weak.

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Duckduckgo Search loads about 1.6k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 622 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~36
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 622 words, ~1,563 tokens.

Download SKILL.mdSave it as .claude/skills/duckduckgo-search/SKILL.md (or your agent's skills folder).

name: duckduckgo-search
description: Free web search via DuckDuckGo - no API key needed. Text, news, images. Use as fallback when other search tools unavailable.
version: 1.0.0
author: hermes-CCC (ported from Hermes Agent by NousResearch)
license: MIT

DuckDuckGo Search

Purpose

Use this skill for lightweight web search without an API key.
It is useful as a fallback when paid search APIs or first-party tools are unavailable.
The library supports text, news, and image search.
This is a pragmatic option for prototyping, research helpers, and lightweight retrieval.

Install

bash

pip install duckduckgo-search

Why Use It

No API key required.
Easy Python integration.
Useful CLI for quick terminal searches.
Supports regions and time filters for fresher results.
Good fallback for general web discovery.

Python API

The main entry point is the DDGS class.
Create a client and call the relevant search method.
Iterate the generator or cast results to a list.

Text Search Example

python

from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = ddgs.text("vector databases for rag", max_results=10)
    for item in results:
        print(item["title"])
        print(item["href"])
        print(item["body"])
        print()

text() is the default choice for general web results.
Use concise queries first, then refine.
Extract only the fields you actually need for downstream processing.

News Search Example

python

from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = ddgs.news(
        keywords="open source llm releases",
        max_results=10,
        region="us-en",
        timelimit="w",
    )
    for item in results:
        print(item["title"])
        print(item["date"])
        print(item["url"])

News search is better than general text search when recency matters.
Useful parameters include keywords, max_results, region, and timelimit.
Prefer short keyword-focused queries over verbose natural language.

Image Search Example

python

from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = ddgs.images("server rack diagram", max_results=10)
    for item in results:
        print(item["title"])
        print(item["image"])

ddgs.images(keywords, max_results) is the simplest path for image discovery.
Verify licensing and usage rights before reuse.
Image results are best for inspiration, references, and visual discovery rather than authoritative facts.

CLI Usage

bash

ddgs text -k "query" -m 10

text runs a standard web search.
-k sets the keywords.
-m 10 limits the maximum number of results.
This is useful for shell scripts or quick ad hoc research.

CLI Patterns

bash

ddgs text -k "python async queue patterns" -m 10
ddgs news -k "gpu inference news" -m 5
ddgs images -k "er diagram examples" -m 8

Use CLI mode when you want zero boilerplate.
Use Python mode when you need structured post-processing.

Regions

wt-wt for global results
us-en for United States English
kr-ko for Korea Korean
regional values can materially change ranking and language mix

Region examples:

python

results = ddgs.text("open banking regulation", region="wt-wt", max_results=10)
results = ddgs.text("AI policy", region="us-en", max_results=10)
results = ddgs.news("반도체 투자", region="kr-ko", max_results=10)

Time Limits

d for day
w for week
m for month
y for year

Use time limits when:

tracking current events
watching new releases
checking recent blog or news coverage
reducing stale results

Rate Limiting

Do not hammer the service with rapid repeated requests.
Add a short sleep between loops or batches.
Cache results locally when queries repeat.
If you are scraping many queries, batch slowly and keep scope tight.

Simple pattern:

python

import time
from duckduckgo_search import DDGS

queries = ["llm evals", "vector db benchmarks", "open source agents"]

with DDGS() as ddgs:
    for q in queries:
        results = list(ddgs.text(q, max_results=5))
        print(q, len(results))
        time.sleep(2)

Query Strategy

Start broad, then narrow.
Prefer keywords over long questions.
Use quotes only when exact phrase matching matters.
Switch to news mode when freshness matters more than general authority.
Use the region parameter intentionally rather than leaving locality to chance.

Show full SKILL.md (236 more words)Show less

Fallback Positioning

No API key required means this is a practical fallback.
It is well suited to a WebSearch fallback path in tools or scripts.
When other providers fail, DDG search can still return useful retrieval candidates.
It should not be treated as a guaranteed enterprise-grade SLA service.

Practical Research Workflow

Run a text search for broad discovery.
Switch to news search for recent developments.
Use images when you need visual references or diagrams.
Save URLs and summarize locally.
Re-run with a region or time filter when result quality is weak.

Output Handling

Normalize fields early because result keys can vary slightly across search modes.
Save title, URL, snippet, source, and date when present.
Store timestamps when using this for repeated monitoring.
Filter duplicates before passing results downstream.

Limitations

Search result shape may evolve with library updates.
Relevance is not identical to large paid search providers.
Image search is discovery-oriented, not rights-cleared asset sourcing.
Heavy automation can trigger blocking or degraded responses.

Summary

Install with pip install duckduckgo-search.
Use the DDGS class for text, news, and image search in Python.
Use ddgs text -k "query" -m 10 for terminal-based search.
For news, pass keywords, max_results, region, and timelimit.
For images, use ddgs.images(keywords, max_results).
Common regions include wt-wt, us-en, and kr-ko.
Common time limits are d, w, m, and y.
Add sleeps between batches and use it as a no-API-key WebSearch fallback.

Files

Just SKILL.md in skills/duckduckgo-search of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

Compare with similar skills

Duckduckgo Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Duckduckgo Search compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Duckduckgo Search this skillAlexAI-MCP/hermes-CCC	135	—	~1.6k	Automated safety check: Pass	MIT	6 mo ago
Discover APIbrightdata/skills	264	—	~2.4k	Automated safety check: Pass	MIT	4 days ago
Ag2 Use Builtin Toolsag2ai/build-with-ag2	252	—	~1.3k	Automated safety check: Pass	Apache-2.0	1 mo ago
Web Accessitwanger/PaiCLI-Python	102	—	~183	Automated safety check: Pass	MIT	2 mo ago
Brightdata SDK JSbrightdata/skills	264	—	~3k	Automated safety check: Pass	MIT	4 days ago
Web Searchfastclaw-ai/fastclaw	1.4k	—	~294	Automated safety check: Pass	Custom licence	yesterday

Similar skills

Discover API
brightdata/skills
Use Bright Data's Discover API — intent-ranked, AI-relevance-scored web search at scale (not keyword SERP).
264 GitHub stars~2.4k tokensUpdated 4 days ago
Productivity & AutomationAuto-check passed
Ag2 Use Builtin Tools
ag2ai/build-with-ag2
Wire AG2 beta's shipped tools into an Agent — both provider-native server-side tools (web search, web fetch, code execution, MCP, image generation, memory) and locally-executed common toolkits…
252 GitHub stars~1.3k tokensUpdated 1 mo ago
Productivity & AutomationAuto-check passed
Web Access
itwanger/PaiCLI-Python
A skill your agent uses for live web research, webpage fetching, login-state browsing, dynamic pages, social sites, and tasks that need current internet evidence.
102 GitHub stars~183 tokensUpdated 2 mo ago
Productivity & AutomationAuto-check passed
Brightdata SDK JS
brightdata/skills
Web data extraction and discovery using the Bright Data JavaScript/TypeScript SDK (@brightdata/sdk).
264 GitHub stars~3k tokensUpdated 4 days ago
Productivity & AutomationAuto-check passed
Web Search
fastclaw-ai/fastclaw
Search the web and fetch web pages. An agent skill from fastclaw-ai/fastclaw.
1.4k GitHub stars~294 tokensUpdated yesterday
Productivity & AutomationAuto-check passed
Duckduckgo Search
Tommy-yw/RunbookHermes
Free web search via DuckDuckGo — text, news, images, videos.
546 GitHub starsUsed in 3 repos~2.1k tokens
Productivity & AutomationAuto-check passed

Questions about Duckduckgo Search

What does Duckduckgo Search do?

Free web search via DuckDuckGo - no API key needed. An agent skill from AlexAI-MCP/hermes-CCC. Duckduckgo Search is an agent skill from AlexAI-MCP/hermes-CCC. Free web search via DuckDuckGo - no API key needed.

When should I use Duckduckgo Search?

Duckduckgo Search fits situations like: tasks that involve Web search.

How do I install Duckduckgo Search in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a claude-code`. Or copy the skill folder (skills/duckduckgo-search in AlexAI-MCP/hermes-CCC) into .claude/skills/duckduckgo-search in your project. Claude Code loads it when a task matches its description.

How do I install Duckduckgo Search in Codex?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a codex`. Or copy the skill folder (skills/duckduckgo-search in AlexAI-MCP/hermes-CCC) into .agents/skills/duckduckgo-search in your project. Codex loads it when a task matches its description.

Can I use Duckduckgo Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/duckduckgo-search, .gemini/skills/duckduckgo-search, .github/skills/duckduckgo-search and .opencode/skills/duckduckgo-search in your project.

What does Duckduckgo Search need to run?

Going by SKILL.md and its folder, Duckduckgo Search needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Duckduckgo Search access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Duckduckgo Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Duckduckgo Search use?

Duckduckgo Search is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Duckduckgo Search use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Duckduckgo Search?

Skills that share tags, products or a category with Duckduckgo Search: Discover API (brightdata/skills, 264 stars), Ag2 Use Builtin Tools (ag2ai/build-with-ag2, 252 stars), Web Access (itwanger/PaiCLI-Python, 102 stars) and Brightdata SDK JS (brightdata/skills, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Duckduckgo Search?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Duckduckgo Search

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

DuckDuckGo Search

Purpose

Install

Why Use It

Python API

Text Search Example

News Search Example

Image Search Example

CLI Usage

CLI Patterns

Regions

Time Limits

Rate Limiting

Query Strategy

Fallback Positioning

Practical Research Workflow

Output Handling

Limitations

Summary

Files

Compare with similar skills

Similar skills

More from AlexAI-MCP/hermes-CCC

Related

Questions about Duckduckgo Search