OpenExecutive is an AI-based virtual executive team that presents one executive persona while using specialist agents for areas such as strategy, finance, people operations, legal work, and operations. It is intended for leaders and managers who need support with decisions, governance, approvals, workplace knowledge, and drafting communications for review. The catalogue contains skills, hooks, a setting, an agent, and an instruction for working with OpenExecutive.
Borrowing it
Nothing to install: this file belongs to SenteLabsAI/OpenExecutive. 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/SenteLabsAI/OpenExecutive/main/CLAUDE.mdgit clone --depth 1 https://github.com/SenteLabsAI/OpenExecutiveWrote 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/sentelabsai/openexecutive/claude-md)<a href="https://agentmods.dev/instructions/sentelabsai/openexecutive/claude-md"><img src="https://agentmods.dev/badge/instructions/sentelabsai/openexecutive/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/sentelabsai/openexecutive/claude-md"><img src="https://agentmods.dev/badge/instructions/sentelabsai/openexecutive/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 | $0.05143 | $0.05143 |
| Opus 5.5 | $0.02057 | $0.02057 |
| Sonnet 5.5 | $0.01029 | $0.01029 |
| Haiku 4.5 | $0.00514 | $0.00514 |
Grade A, and why
OpenExecutive 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Executive — Claude Code Context
Project Overview
Open Executive is a multi-agent AI system acting as a virtual corporate executive. Python backend (FastAPI) + Next.js 15 frontend. The "Executive" is a single coherent persona backed by 9 specialist sub-agents, all powered by the Anthropic Claude API.
Repository Layout
packages/core/ Python: all agent logic, API, CLI
packages/ui/ Next.js 15 web UI
knowledge/ Curated MBA knowledge base (git-tracked Markdown)
evals/ Eval scenarios + LLM-as-judge runner
docker/ Dockerfile + docker-compose.yml
.github/workflows/ CI + eval pipeline
Key Commands
make dev # Start FastAPI (port 8000) + Next.js (port 3000)
make test # Run pytest
make lint # ruff check + mypy
make test-changed # fast loop: only the tests that cover what this branch changed
make check # everything CI checks: lint, unit tests, UI build (if touched), PR rules
make eval # Run eval suite against localhost
make docker # docker compose up --build
Python Setup
Uses uv for package management.
cd packages/core
uv sync
source .venv/bin/activate
Architecture — How the Agent System Works
- User message arrives at
Executive(orchestrator inorchestrator/executive.py) - Executive uses Anthropic tool use to call
consult_specialistfor relevant domains - For cross-domain questions, multiple specialists are called in parallel
- Each specialist:
- Gets its domain system prompt from
prompts/domain_prompts.py - Retrieves relevant chunks from ChromaDB (built-in knowledge + company docs)
- Returns analysis to the Executive
- Gets its domain system prompt from
- Executive synthesizes all specialist input into one coherent response
- The internal agent architecture is NEVER exposed to the user
Prompt Caching — Critical
The system is designed around Anthropic prompt caching. Breaking caching = 10x cost increase.
Never put dynamic content in system prompt blocks that have cache_control.
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 Changed · +24 tokens per session feaf4187b353
- 8d ago Changed · +29 tokens per session a2f9670ef549
- 16d ago Changed 82eb0f828825
- 22d ago Changed · +7 lines · +111 tokens per session c43dc88bacf0
- 25d ago Changed · +41 tokens per session d4fcd0e3e62d
- 27d ago Changed · +1 lines · +345 tokens per session a951806ff31e
- 28d ago Changed · +2 lines · +202 tokens per session d6f217a73b74
- 29d ago Changed · +34 tokens per session 71aea6b6481c
- 1mo ago Changed · +70 tokens per session a3c8e733f9ac
- 1mo ago First seen · 283 lines · 4,287 tokens per session scan A 9bdc8bf972f2
OpenExecutive CLAUDE.md is an instructions file published in the GitHub repository SenteLabsAI/OpenExecutive (5,703 stars, last pushed today), licensed Apache-2.0. It adds 5,143 tokens to every session, about $0.0206 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.