What is mcp-web-hound AGENTS.md?

Project instructions for mcp-web-hound, a tool that searches the web through multiple providers. They define code structure, configuration, caching, spending limits, and how search providers must connect.

Use them when changing the mcp-web-hound TypeScript project, especially its search providers, configuration, caching, or search tools.

They keep development consistent and prevent search results from bypassing required caching, budget checks, or project interfaces.

How ilgizar-valiullin/mcp-web-hound configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ilgizar-valiullin/mcp-web-hound. 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/ilgizar-valiullin/mcp-web-hound/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ilgizar-valiullin/mcp-web-hound

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/ilgizar-valiullin/mcp-web-hound/agents-md/github.svg)](https://agentmods.dev/instructions/ilgizar-valiullin/mcp-web-hound/agents-md)

Your own site

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

Per session 519 This file is loaded in full into every session.

When invoked 519 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	$0.00519	$0.00519
Opus 5	$0.00260	$0.00260
Sonnet 5	$0.00104	$0.00104
Haiku 4.5	$0.00052	$0.00052

Measured 11d ago against content hash 4b46c54a6838, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-web-hound 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 11d 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 · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Web Hound — Agent Rules

Project-specific rules

No code changes without plan approval. This project follows the planning mode protocol.
TypeScript only. All source code in src/ must be TypeScript with strict mode enabled.
Provider interface. All search providers MUST implement the SearchProvider interface defined in src/search/providers/base-provider.ts. No ad-hoc provider implementations.
Web search via orchestrator only. The src/tools/search.ts layer must only call the orchestrator. All web-search provider logic stays in src/search/. GitHub/GitLab tools (github-search.ts, gitlab-search.ts) are separate API tools, not part of the web-search pipeline.
Cache invariant. Every successful provider response MUST be cached before returning to the agent. No uncached responses.
Budget enforcement. Budget check MUST happen before any provider call. No exceptions.
Env-based config. All configurable values come from environment variables (.env). Use npx mcp-web-hound configure --json get/set for machine-readable access. Two-tier model: ~/.config/mcp-web-hound/.env (main) + project .env (per-folder overrides). Agents must only write to server .env.
Logging. Use pino structured logger. No console.log in production code.
Error handling. Provider errors must never crash the server. Log, mark unhealthy, fallback to next provider.
Documentation. After any architectural change, update the corresponding doc in docs/ and the flow diagram in docs/diagrams/.
Tests before merge. Every feature or fix MUST include tests. Run npm test before committing. For live provider testing, set API keys in .env and run npm run test:providers.
Coverage check. After adding tests, verify coverage doesn't regress: npm run test:coverage. Current thresholds: statements 50%, branches 35%, functions 55%, lines 55%.
Search log versioning. Every entry in the training dataset carries system_version for provenance. The ranker and signals versions are defined as constants in src/search/reranker.ts (RERANKER_VERSION, SIGNALS_VERSION). The mcp version comes from package.json.

Read the full file on GitHub · 30 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.

11d ago First seen · 30 lines · 519 tokens per session scan A 4b46c54a6838

Subscribe to this mod's changes

mcp-web-hound AGENTS.md is an instructions file published in the GitHub repository ilgizar-valiullin/mcp-web-hound (18 stars, last pushed 2mo ago), licensed MIT. It adds 519 tokens to every session, about $0.0026 per session on Opus 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-web-hound: Instructions file for Codex