What is zero_api_key_web_search?

A web-search and page-reading skill for Codex that gathers sources and checks whether factual claims are supported. It can search across several engines and handle some blocked pages.

Use it to search the web, read pages, check claims, and produce evidence reports with source-backed findings.

It helps verify changing or uncertain information instead of relying on unsupported statements.

How wd041216-bit/zero-api-key-web-search configures Codex

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/.codex/SKILL.md

Clone the repo

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

Made for: Codex.

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

Your own site

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

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 597 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	$0.00066	$0.00597
Opus 5.5	$0.00026	$0.00239
Sonnet 5.5	$0.00013	$0.00119
Haiku 4.5	$0.00007	$0.00060

Measured 1mo ago against content hash fd5b8715630e, 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.

.codex/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zero-API-Key Web Search for Codex

Use this skill when Codex needs current information, supporting citations, or a compact evidence report before answering.

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

zero-verify is heuristic and evidence-aware, not a proof engine.
The default path still starts with ddgs.
Bright Data is optional and should not receive queries unless configured or requested.

Read the full file on GitHub · 65 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 fd5b8715630e
2mo ago First seen · 65 lines · 66 tokens per session scan A 2855af4a3881

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 66 tokens to every session and 597 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	66	Codex
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 Codex