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.
curl -O https://raw.githubusercontent.com/wd041216-bit/zero-api-key-web-search/main/GEMINI.mdgit clone --depth 1 https://github.com/wd041216-bit/zero-api-key-web-searchWrote 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/instructions/wd041216-bit/zero-api-key-web-search/gemini-md)<a href="https://agentmods.dev/instructions/wd041216-bit/zero-api-key-web-search/gemini-md"><img src="https://agentmods.dev/badge/instructions/wd041216-bit/zero-api-key-web-search/gemini-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.
<a href="https://agentmods.dev/instructions/wd041216-bit/zero-api-key-web-search/gemini-md"><img src="https://agentmods.dev/badge/instructions/wd041216-bit/zero-api-key-web-search/gemini-md.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 | $0.00392 | $0.00392 |
| Opus 5.5 | $0.00157 | $0.00157 |
| Sonnet 5.5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
zero-api-key-web-search GEMINI.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 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.
What it actually says
Zero-API-Key Web Search for Gemini CLI
Use Zero-API-Key Web Search when Gemini needs live search results, source-backed verification, or page-level reading.
Install
pip install zero_api_key_web_search
Minimum verification
zero-search "latest Python release" --type news --timelimit w
zero-verify "Python 3.13 is the latest stable release" --deep --max-pages 2 --json
zero-browse "https://docs.python.org/3/whatsnew/"
zero-report "Python 3.13 stable release" --claim "Python 3.13 is the latest stable release" --deep --json
When to trigger
- Use
zero-searchbefore answering time-sensitive or factual questions. - Use
zero-browsewhen snippets are too thin to support an answer. - Use
zero-verifyfor explicit support/conflict analysis. - Use
zero-reportwhen Gemini needs a concise, citation-ready evidence package. - Prefer the free
ddgs + self-hosted searxngpath when you want stronger provider diversity. - Use
--deepwhen the claim matters enough to justify page-aware verification.
What success looks like
Look for:
- a structured verdict such as
supported,contested, orlikely_false - explicit
provider_diversityandpage_awarefields - supporting or conflicting sources that can be cited directly
When not to over-trust it
- when only one provider is configured
- when snippets and fetched pages are both sparse
- when the claim needs full-document reasoning or domain-specific expertise
Limits
- The default provider path is
ddgs. zero-verifyis heuristic and can misread ambiguous snippets.- Conflicting sources should be surfaced to the user rather than flattened into certainty.
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 2a40f97957b3
- 2mo ago First seen · 48 lines · 392 tokens per session scan A a775e8411a78
zero-api-key-web-search GEMINI.md is an instructions file published in the GitHub repository wd041216-bit/zero-api-key-web-search (20 stars, last pushed 1mo ago), licensed MIT. It adds 392 tokens to every session, about $0.0016 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.
zero-api-key-web-search GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zero-api-key-web-search GEMINI.mdwd041216-bit/zero-api-key-web-search | Instructions file | 20 | 1mo ago | MIT | A | 392 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |