What is zero_api_key_web_search?

A command-line skill for web searching, reading pages, and checking claims against sources. A source-backed answer is one that links statements to information found in those sources.

Use it to search for information, browse a URL, verify a claim, or create a compact evidence report with sources.

It helps an assistant handle current information and reduce unsupported claims. It can also try different search providers when a page or search service is unavailable.

How wd041216-bit/zero-api-key-web-search configures Claude Code and Ge

Reuse

Borrowing it

Nothing to install: this file belongs to wd041216-bit/zero-api-key-web-search. 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/wd041216-bit/zero-api-key-web-search/main/.gemini/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/wd041216-bit/zero-api-key-web-search

Made for: Claude Code, Gemini CLI.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wd041216-bit/zero-api-key-web-search/gemini/github.svg)](https://agentmods.dev/skills/wd041216-bit/zero-api-key-web-search/gemini)

Your own site

<a href="https://agentmods.dev/skills/wd041216-bit/zero-api-key-web-search/gemini"><img src="https://agentmods.dev/badge/skills/wd041216-bit/zero-api-key-web-search/gemini/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wd041216-bit/zero-api-key-web-search/gemini"><img src="https://agentmods.dev/badge/skills/wd041216-bit/zero-api-key-web-search/gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 618 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.00618
Opus 5.5	$0.00027	$0.00247
Sonnet 5.5	$0.00013	$0.00124
Haiku 4.5	$0.00007	$0.00062

Measured 1mo ago against content hash 813fd4a99cca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zero_api_key_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.

.gemini/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zero-API-Key Web Search for Gemini CLI

Use this skill when Gemini needs current information, supporting citations, or a compact evidence report before answering. The default path is free; optional providers are discoverable for stronger coverage.

Install

pip install zero_api_key_web_search

Core Commands

zero-search "latest Python release" --type news --timelimit w
zero-search providers
zero-browse "https://docs.python.org/3/whatsnew/"
zero-verify "Python 3.13 is the latest stable release" --deep --max-pages 2 --json
zero-report "Python 3.13 stable release" --claim "Python 3.13 is the latest stable release" --deep --json
zero-setup  # Interactive provider configuration wizard

Provider paths

Profile	Providers	Best for
`free`	ddgs	Zero-setup local search
`free-verified`	ddgs, searxng	Free cross-validation
`production`	brightdata	Production reliability and geo-targeting
`production-unlock`	brightdata, web_unlocker	Production SERP + blocked page access
`max-evidence`	ddgs, searxng, brightdata	Maximum provider diversity

When to Use

time-sensitive questions about releases, dates, people, or statistics
factual claims that should be checked before being stated confidently
reading pages that return 403 or require geo-targeted access
workflows where conflicting evidence should be surfaced instead of hidden

Guidance

Start with zero-search for live facts and recent changes.
Use zero-browse when snippets are too thin — it auto-unlocks blocked pages via Web Unlocker.
Use --engine bing/yandex/baidu/... with Bright Data for multi-engine SERP results.
Use zero-verify for support/conflict classification.
Use zero-report when you want one compact output with verdict, citations, and next steps.
Use optional brightdata only when configured or explicitly requested. New users can sign up at https://get.brightdata.com/h21j9xz4uxgd.

Limits

Read the full file on GitHub · 66 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.

1mo ago Changed 813fd4a99cca
2mo ago First seen · 66 lines · 67 tokens per session scan A 0f474bd8b4f1

Subscribe to this mod's changes

zero_api_key_web_search is a skill published in the GitHub repository wd041216-bit/zero-api-key-web-search (20 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 618 once invoked, about $0.0003 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 2026-08-30.

Research ai-agents fact-checking jev mcp model-context-protocol web-search

zero_api_key_web_search next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zero_api_key_web_searchwd041216-bit/zero-api-key-web-search	Skill	20	1mo ago	MIT	A	67	Claude Code, Gemini CLI
keenable-web-searchkeenableai/keenable-mcp	Skill	6	yesterday	MIT	A	73	Claude Code, Codex
unbrowserprotostatis/unbrowser	Skill	17	2mo ago	Apache-2.0	A	40	Claude Code, Codex
lenz-fact-checklenzhq/lenz-mcp	Skill	0	5d ago	Apache-2.0	A	178	Claude Code
firecrawl-monitorfirecrawl/skills	Skill	147	2d ago	ISC	A	50	Claude Code
dcc-blender-assembly-pitfallsdcc-mcp/dcc-mcp-blender	Skill	60	yesterday	MIT	A	153	Claude Code
read-literaturefirecrawl/firecrawl-claude-plugin	Skill	255	3d ago	MIT	A	101	Claude Code

zero-api-key-web-search: Skill for Claude Code