Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sifter-ai/sifter/claude-mdgit clone --depth 1 https://github.com/sifter-ai/sifterWrote 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/sifter-ai/sifter/claude-md)<a href="https://agentmods.dev/instructions/sifter-ai/sifter/claude-md"><img src="https://agentmods.dev/badge/instructions/sifter-ai/sifter/claude-md.svg" alt="Measured on agentmods" 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 | $0.01169 | $0.01169 |
| Opus 5 | $0.00584 | $0.00584 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
sifter 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 4d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is Sifter
Sifter is an AI-powered document extraction engine. It takes homogeneous document collections (invoices, contracts, receipts) and extracts structured fields into MongoDB, making them queryable with natural language. It is not a RAG system — it generates exact MongoDB aggregation pipelines, not similarity-based results.
Monorepo Structure
All packages live under code/:
| Package | Path | Language |
|---|---|---|
| Backend API | code/server/ |
Python (FastAPI) |
| Frontend | code/frontend/ |
TypeScript (React + Vite) |
| Python SDK | code/sdk/ |
Python |
| TypeScript SDK | code/sdk-ts/ |
TypeScript |
| CLI | code/cli/ |
TypeScript (Commander.js) |
| MCP Server | code/mcp/ |
Python |
Commands
Backend (code/server/)
uv sync # install dependencies
uv run sifter-server # start FastAPI on port 8000
uv run pytest # run all tests (requires MongoDB on localhost:27017)
uv run pytest tests/test_foo.py::test_bar # run single test
Frontend (code/frontend/)
npm install
npm run dev # Vite dev server on port 3000
npm run build
npm run lint # ESLint
npx tsc --noEmit # type check
npm test # Vitest
TypeScript SDK (code/sdk-ts/)
npm test # Vitest
MCP Server (code/mcp/)
uv run pytest
Full Stack (Docker)
# from code/ directory, after creating .env from server/.env.example
docker compose up -d
The backend serves the built frontend as static files, so docker compose gives a single unified deployment.
Backend Architecture
Entry: server/sifter/server.py — creates the FastAPI app, registers routers, starts background workers, optionally mounts MCP at /mcp.
Key layers:
sifter/api/— FastAPI routers (sifts, documents, aggregations, chat, folders, auth, webhooks, dashboards, keys, config)sifter/services/— business logic; the most important services are:SiftService— sift lifecycle (create, schema inference, extraction orchestration)DocumentProcessor— async background queue that dispatches extraction jobsSiftAgent/ExtractionAgent— LLM agents that extract fields from documentsAggregationService/PipelineAgent— converts natural language queries to MongoDB aggregation pipelinesDashboardService— auto-generates dashboard specs from sift data
sifter/models/— Pydantic models (Sift, Document, SiftResult, Extraction, User)sifter/prompts/— LLM system prompts used by agentssifter/db.py— Motor async MongoDB clientsifter/storage.py— abstract file storage (filesystem / S3 / GCS)
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.
- 4d ago First seen · 107 lines · 1,169 tokens per session scan A be4acbe13693
sifter CLAUDE.md is an instructions file published in the GitHub repository sifter-ai/sifter (55 stars, last pushed 2mo ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0058 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
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.