KiwiQ is a Python platform for defining and running multi-agent workflows as JSON or Python graphs, with memory, human review, provider integrations, and observability. It is for teams building multi-step AI processes such as research, content creation, diagnostics, and lead scoring.
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/rcortx/kiwiq/claude-mdgit clone --depth 1 https://github.com/rcortx/kiwiqWrote 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/rcortx/kiwiq/claude-md)<a href="https://agentmods.dev/instructions/rcortx/kiwiq/claude-md"><img src="https://agentmods.dev/badge/instructions/rcortx/kiwiq/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 5.1 | $0.05206 | $0.05206 |
| Opus 5 | $0.02603 | $0.02603 |
| Sonnet 5 | $0.01041 | $0.01041 |
| Haiku 4.5 | $0.00521 | $0.00521 |
Grade A, and why
kiwiq 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 6d 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 — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
IMPORTANT: Once you set yourself some todos, you should complete them without stopping, unless you have some particular reason to stop (e.g. you need to ask a question, you need feedback / input, etc.) If you do stop before finishing all todos, you MUST state the reason why you're stopping. We'll call this the "no-stop" rule. If you stop before finishing todos, and don't give any reason why you've stopped, I'll be very disappointed, and I'll ask you why you didn't follow the "no-stop rule." Never be lazy and ask me obvious questions, just to stop in between completing your TODOs!
DON"T USE SED for EDITING!!
Never duplicate, redundant code, keep it modular and reuse it, maybe create shared helper utils which is better maintainable in the long term.
Project Overview
KiwiQ AI Platform - A multi-service, multi-tier Kubernetes-based platform for AI-powered workflow orchestration with LangGraph, Prefect, and comprehensive integrations for LLM providers, scraping, and customer data management.
Tech Stack:
- Python 3.12 (dictated by Airflow compatibility)
- Poetry for dependency management
- FastAPI for REST APIs
- Prefect for workflow orchestration
- LangGraph for workflow graphs
- PostgreSQL (via SQLModel/SQLAlchemy/Alembic)
- MongoDB (customer data, versioned documents)
- Redis (caching, queuing)
- RabbitMQ (event streaming)
- Weaviate (vector database)
- Docker Compose for local development
Repository Structure
kiwiq-backend/
├── libs/src/ # Shared cross-service libraries
│ ├── db/ # Database clients, models, migrations (Alembic)
│ ├── global_config/ # Global settings
│ ├── global_utils/ # Shared utilities
│ ├── mongo_client/ # MongoDB client
│ ├── rabbitmq_client/ # RabbitMQ client
│ ├── redis_client/ # Redis client
│ └── weaviate_client/ # Weaviate vector DB client
├── services/
│ ├── kiwi_app/ # Core FastAPI application
│ │ ├── auth/ # Authentication & authorization
│ │ ├── billing/ # Stripe billing & credits
│ │ ├── workflow_app/ # Workflow backend APIs
│ │ │ ├── routes.py # Workflow execution endpoints
│ │ │ ├── websockets.py # Real-time workflow updates
│ │ │ ├── event_consumer.py # RabbitMQ event processing
│ │ │ └── app_state.py # Application state management
│ │ ├── data_jobs/ # Data ingestion & RAG
│ │ ├── rag_service/ # RAG query endpoints
│ │ └── main.py # FastAPI app entrypoint
│ ├── workflow_service/ # Core workflow engine
│ │ ├── registry/ # Node & workflow registry
│ │ │ ├── nodes/ # All node implementations
│ │ │ │ ├── core/ # Core nodes (router, map_list_router, etc.)
│ │ │ │ ├── llm/ # LLM nodes with tool support
│ │ │ │ ├── data_ops/ # Transform, merge, aggregate
│ │ │ │ ├── db/ # Customer data CRUD nodes
│ │ │ │ ├── scraping/ # LinkedIn & web scraping nodes
│ │ │ │ └── tools/ # Document CRUD tools
│ │ │ ├── schemas/ # Base schemas & reducers
│ │ │ └── workflows/ # Workflow definitions
│ │ ├── graph/ # Graph builder & runtime
│ │ │ ├── builder.py # GraphSchema -> LangGraph
│ │ │ ├── graph.py # GraphSchema definitions
│ │ │ └── runtime/ # LangGraph runtime adapter
│ │ └── services/
│ │ ├── worker.py # Prefect worker entrypoint
│ │ ├── scraping/ # Web scraping service
│ │ └── external_context_manager.py
│ ├── linkedin_integration/ # LinkedIn OAuth & API
│ └── scraper_service/ # Scraping API routes
├── standalone_test_client/ # Workflow testing client
│ └── kiwi_client/ # Test workflows & utilities
├── tests/
│ ├── unit/ # Unit tests
│ └── integration/ # Integration tests
├── docs/design_docs/ # Architecture documentation
├── docker/ # Docker configurations
├── pyproject.toml # Poetry dependencies
└── pytest.ini # Test configuration
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.
- 6d ago First seen · 557 lines · 5,206 tokens per session scan A ea12e0f9b56d
kiwiq CLAUDE.md is an instructions file published in the GitHub repository rcortx/kiwiq (1,903 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 5,206 tokens to every session, about $0.0260 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
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.
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.
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).