Borrowing it
Nothing to install: this file belongs to LastSearch-HQ/lastsearch. 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/LastSearch-HQ/lastsearch/main/CLAUDE.mdgit clone --depth 1 https://github.com/LastSearch-HQ/lastsearchWrote 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/lastsearch-hq/lastsearch/claude-md)<a href="https://agentmods.dev/instructions/lastsearch-hq/lastsearch/claude-md"><img src="https://agentmods.dev/badge/instructions/lastsearch-hq/lastsearch/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/lastsearch-hq/lastsearch/claude-md"><img src="https://agentmods.dev/badge/instructions/lastsearch-hq/lastsearch/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 | $0.02600 | $0.02600 |
| Opus 5 | $0.01300 | $0.01300 |
| Sonnet 5 | $0.00520 | $0.00520 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
lastsearch 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 10d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — LastSearch
What this project is
LastSearch is open-source research infrastructure for AI agents. It gives agents real-time web search with evidence-backed citations and confidence scores. Available as MCP server, REST API, and Python SDK.
Tagline: Reliable Research Infrastructure for AI Agents
Monorepo structure
apps/mcp/ — MCP server (npm: lastsearch)
packages/shared/ — Shared types, schemas, constants
packages/python-sdk/ — Python SDK (PyPI: lastsearch)
src/ — Vite + React frontend (landing, developers, playground pages)
The verification engine (Fastify REST API) has been moved to a separate private repository: lastsearch-hq/lastsearch-engine. The public repo's frontend proxies
/api/*requests to the hosted engine.
Two-Repo Architecture
This project spans two repositories. Always consider both when making changes:
| Repo | Visibility | What lives here | Deploys to |
|---|---|---|---|
| lastsearch (this repo) | Public (Apache 2.0) | MCP server, Python SDK, frontend, shared types, examples, docs | Vercel (frontend + MCP function) |
lastsearch-engine (/tmp/lastsearch-engine) |
Private (BSL 1.1) | Verification engine, API routes, NLI, confidence scoring, Redis cache, Supabase | Vercel (separate project) |
When making changes:
- API parameter changes → update engine routes + MCP tool schemas + Python SDK methods + shared types
- New features → engine implementation + public repo surfaces (MCP, SDK, docs, frontend)
- Auth/key changes → both repos (engine auth middleware + MCP/SDK client code)
- Version bumps → public repo only (MCP package.json + index.ts, Python SDK pyproject.toml + init.py)
All API access requires a LastSearch key (ls_xxx). There is no BYOK (bring your own keys) mode. The engine handles all search and LLM calls server-side.
Key commands
pnpm dev:web # Frontend only (Vite)
pnpm build # Full build (Vercel)
pnpm test # Run tests (vitest)
npx pnpm --filter lastsearch build # Build MCP only
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.
- 10d ago First seen · 155 lines · 2,600 tokens per session scan A 7c205f3f473d
lastsearch CLAUDE.md is an instructions file published in the GitHub repository LastSearch-HQ/lastsearch (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,600 tokens to every session, about $0.0130 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.
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).
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.
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.