What is hive-web AGENTS.md?

Project-specific instructions for hive-web, a local server for compact web search, extracting page content, and controlled browser sessions. They define code boundaries, compact outputs, secret handling, testing, and safety checks for sensitive actions.

Use them when modifying hive-web or reviewing changes to its web-search and browser features.

They keep browser and web-search changes consistent, limit unnecessary data, and protect payment, password, two-factor, and CAPTCHA actions.

How YegorMy/hive-web configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to YegorMy/hive-web. 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/YegorMy/hive-web/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/YegorMy/hive-web

Made for: Codex, OpenCode.

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/instructions/yegormy/hive-web/agents-md/github.svg)](https://agentmods.dev/instructions/yegormy/hive-web/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yegormy/hive-web/agents-md"><img src="https://agentmods.dev/badge/instructions/yegormy/hive-web/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yegormy/hive-web/agents-md"><img src="https://agentmods.dev/badge/instructions/yegormy/hive-web/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 144 This file is loaded in full into every session.

When invoked 144 The same file — it is already loaded in full.

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	$0.00144	$0.00144
Opus 5.5	$0.00058	$0.00058
Sonnet 5.5	$0.00029	$0.00029
Haiku 4.5	$0.00014	$0.00014

Measured 2mo ago against content hash 0f02755fea91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hive-web AGENTS.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 2mo 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.

AGENTS.md · 10 lines

What it actually says

hive-web-runtime agent rules

Keep the module boundary: static-web must not import action-web; action-web may import static-web.
Default outputs must be token-cheap compact snapshots, not full HTML/DOM/screenshots.
Raw payloads belong in the artifact store and should be referenced by artifact_id.
Do not add secrets to config files. Use env vars or client-specific secret stores.
Run uv run pytest -q before declaring changes complete.
For live browser changes, also smoke-test a headless session against https://example.com.
Never remove the safety gate around payment/password/2FA/captcha-looking actions without explicit user request.

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.

2mo ago First seen · 10 lines · 144 tokens per session scan A 0f02755fea91

Subscribe to this mod's changes

hive-web AGENTS.md is an instructions file published in the GitHub repository YegorMy/hive-web (0 stars, last pushed 3mo ago), licensed MIT. It adds 144 tokens to every session, about $0.0006 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.

firecrawl hermes-agent mcp playwright searxng web-automation

hive-web AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hive-web AGENTS.mdYegorMy/hive-web	Instructions file	0	3mo ago	MIT	A	144	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	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

hive-web: Instructions file for Codex