web-researcher-mcp: Instructions file for Claude Code

CLAUDE.md

web-researcher-mcp CLAUDE.md is an instructions file for Claude Code from zoharbabin/web-researcher-mcp. It costs 5,745 tokens per session, scanned A, original, MIT.

Project instructions for a Go-based web-research MCP server, which lets AI assistants search the web, extract page content, and combine information from multiple sources. They describe its commands, architecture, tests, and security checks.

In plain words
What is it for?
They help maintain the server, run unit and integration tests, check for vulnerabilities, and verify its Go and Python components.
Why use it?
They give developers the project-specific rules for building, testing, linting, and validating changes without relying on guesswork.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is zoharbabin/web-researcher-mcp's own configuration. It tells Claude Code how to work on web-researcher-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything web-researcher-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zoharbabin/web-researcher-mcp. 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/zoharbabin/web-researcher-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zoharbabin/web-researcher-mcp

Made for: Claude Code.

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.

agentmods badge for web-researcher-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zoharbabin/web-researcher-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/zoharbabin/web-researcher-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zoharbabin/web-researcher-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zoharbabin/web-researcher-mcp/claude-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.

agentmods 80×15 button for web-researcher-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zoharbabin/web-researcher-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zoharbabin/web-researcher-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,745 This file is loaded in full into every session.
When invoked 5,745 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05745 $0.05745
Opus 5 $0.02873 $0.02873
Sonnet 5 $0.01149 $0.01149
Haiku 4.5 $0.00575 $0.00575

Measured 11d ago against content hash 2968913fe8de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

web-researcher-mcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

bin/ # Claude Code plugin installer (bin/install.sh) — distinct from the root curl installer install.sh
CLAUDE.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — web-researcher-mcp

An MCP server in Go that gives AI assistants web search, content extraction, and multi-source research capabilities over STDIO or HTTP transport.

Commands

go build -o web-researcher-mcp ./cmd/web-researcher-mcp    # Build
go test ./...                                               # Unit + integration tests
go test -race ./...                                         # Race detector
go test -tags=e2e -count=1 ./tests/e2e/...                  # E2E (needs e2e build tag + API keys)
go test -tags=live ./...                                    # Live external-API tests (needs API keys)
go tool golangci-lint run                                   # Lint (pinned version)
go tool govulncheck ./...                                   # Vulnerability scan (pinned version)
make verify                                                 # Full CI gate: fmt-check + vet + lint + sec + vuln + validate-lenses + test-race + test-e2e + check-python-drift + test-python + build
make test-python                                            # Python SDK unit + integration tests (mock HTTP server, no binary)
make test-python-live                                       # Python SDK live E2E tests (builds Go binary; needs internet)
make rebuild-local                                          # Clear caches + rebuild + reinstall (macOS-SIGKILL-safe); ARGS="--no-install" to build only

Prefer make for CI-gated targets — they carry the right flags, pinned tools, and correct sequencing. Use raw go commands for one-off interactive use only.

Contribution Rules

  • Never push directly to main. All changes go through a branch and a pull request — no exceptions, including chore commits and one-liners.
  • Commit format: type(scope): subject [(#PR)] — types: feat, fix, chore, docs, refactor, test, ci. Examples: fix(config): validate CACHE_ENCRYPTION_KEY · chore: bump VERSION to 1.36.4 · docs: full zero-drift audit.
  • After any edit to lenses/: run make sync-lenses before committing — copies changes into internal/search/lenses_embed/. TestEmbeddedLensesMatchRoot fails CI if they diverge.
  • After any tool schema change: run make gen-python-client, then stage and commit the regenerated python/web_researcher_mcp/{models.py,client.py,__init__.py} in the same commit. The python-drift CI job and the pre-commit hook both fail if you skip this.
  • GitHub issues are specs, not scratchpads. An issue body states current codebase state and what to build — concise, concrete, ready to implement. Never post a comment narrating your own investigation, hedges, or "here's what I checked" reasoning — that's internal process, not spec content, and it wastes tokens for every agent that reads the issue afterward. When an issue's cited state goes stale (a blocker ships, a file moves), edit the body in place to reflect current reality — don't append a comment layering old-vs-new. Comments are for genuine back-and-forth with external contributors only.

Read the full file on GitHub · 204 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.

  1. 11d ago First seen · 204 lines · 5,745 tokens per session scan A 2968913fe8de

Subscribe to this mod's changes

web-researcher-mcp CLAUDE.md is an instructions file published in the GitHub repository zoharbabin/web-researcher-mcp (57 stars, last pushed 2d ago), licensed MIT. It adds 5,745 tokens to every session, about $0.0287 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens