Borrowing it
Nothing to install: this file belongs to Tannnnhauser/pivot-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/Tannnnhauser/pivot-web-search/main/CLAUDE.mdgit clone --depth 1 https://github.com/Tannnnhauser/pivot-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/tannnnhauser/pivot-web-search/claude-md)<a href="https://agentmods.dev/instructions/tannnnhauser/pivot-web-search/claude-md"><img src="https://agentmods.dev/badge/instructions/tannnnhauser/pivot-web-search/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.
<a href="https://agentmods.dev/instructions/tannnnhauser/pivot-web-search/claude-md"><img src="https://agentmods.dev/badge/instructions/tannnnhauser/pivot-web-search/claude-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 | $0.01805 | $0.01805 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
pivot-web-search CLAUDE.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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pivot Web Search
This is a Claude Code Plugin repository. It replaces Claude Code's built-in WebSearch and WebFetch tools with a configurable failover search engine (DDG -> Tavily -> Brave -> Gemini) and content extraction with optional JS rendering fallback.
Plugin Installation Context
Users install this plugin at different scopes. All design and implementation decisions must account for all three:
- User scope (
~/.claude.json) — available across all projects on the user's machine - Project scope (
.mcp.jsonat project root, checked into VCS) — shared with team members - Local scope (
~/.claude.jsonunder project path) — private to one user in one project
Implications:
- File paths must use
${CLAUDE_PLUGIN_ROOT}— never assume a fixed install location - Runtime cache (quota, proxy hints, debug logs) goes to
~/.cache/pivot-web-search/(user-global) - User-editable advanced YAML config goes to
~/.pivot-web-search/(providers.yaml,proxies.yaml); templates live atexamples/in this repo - Hooks (PreToolUse, SessionStart) apply at whatever scope the plugin is enabled — they affect all sessions in that scope
- Environment variables from
userConfigare injected by Claude Code at runtime, not read from disk - The plugin must work correctly whether it's the only plugin installed or one of many
Tool Usage
- NEVER call the built-in WebSearch or WebFetch tools. They are denied by this plugin's PreToolUse hook with a deny reason pointing to the MCP equivalents.
- Use the MCP server tools instead:
mcp__pivot-web-search__WebSearchandmcp__pivot-web-search__WebFetch. - These are available to all agent types including Explore and Plan subagents.
Three Tools
mcp__pivot-web-search__WebSearch— Search the web. Quota-aware provider failover with quality detection and smart defaults. Auto-detects time-sensitive and news queries. Supports provider selection, domain filtering, news search, super mode (all providers in parallel). Useinclude_content=trueto get pre-extracted page content with results (via Brave LLM Context API).mcp__pivot-web-search__WebFetch— Extract full page content from URLs. Uses trafilatura with Next.js/Nuxt.js SPA fallback. Configurable JS renderer fallback (Playwright or Tavily Extract) for dynamic pages. Supports batch URLs, query-aware extraction, and configurable truncation.mcp__pivot-web-search__WebSearchConfig— Runtime config inspection (status) and hot-reload (reload). Status includes provider health and quota usage.
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.
- 9d ago First seen · 106 lines · 1,805 tokens per session scan A 9a8bc0262464
pivot-web-search CLAUDE.md is an instructions file published in the GitHub repository Tannnnhauser/pivot-web-search (3 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,805 tokens to every session, about $0.0090 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 2026-08-31.
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.