What is VentureBot AGENTS.md?

Repository instructions for VentureBot, a project with a Python backend, React frontend, agent configuration, documentation, scripts, and local data.

Setting up the development environment, running the backend or frontend, using Docker, building the application, and following the project's guidelines.

They give an agent the project layout, setup commands, coding conventions, and testing expectations needed to work consistently in the repository.

VentureBot AGENTS.md — Instructions file for Codex and OpenCode by gies-ai-experiments: Repository instructions for VentureBot, a project wi

Install

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.

agentmods

npx agentmods add instructions/gies-ai-experiments/venturebot/agents-md

Clone the repo

git clone --depth 1 https://github.com/gies-ai-experiments/VentureBot

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gies-ai-experiments/venturebot/agents-md.svg)](https://agentmods.dev/instructions/gies-ai-experiments/venturebot/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gies-ai-experiments/venturebot/agents-md"><img src="https://agentmods.dev/badge/instructions/gies-ai-experiments/venturebot/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 660 This file is loaded in full into every session.

When invoked 660 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00660	$0.00660
Opus 5	$0.00330	$0.00330
Sonnet 5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured 5d ago against content hash 22a318e49507, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

VentureBot AGENTS.md scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Smoke check: `curl http://localhost:8000/healthz` and a simple chat session via `POST /api/chat/sessions`.

AGENTS.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

services/: Python backend (FastAPI gateway in services/api_gateway/app/, orchestration in services/orchestrator/, shared tools in services/tools/)
crewai-agents/: CrewAI blueprint + prompt/task configs (crewai-agents/src/venturebot_crew/config/*.yaml)
frontend/: React + Vite SPA (TypeScript) and nginx container for production builds
docs/, scripts/, data/: architecture notes, ops scripts, local runtime data (SQLite/logs)

Build, Test, and Development Commands

Backend setup: python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
Run backend (dev): python -m uvicorn services.api_gateway.app.main:app --reload --port 8000 (docs: http://localhost:8000/docs)
Frontend setup: cd frontend && npm ci
Run frontend (dev): cd frontend && npm run dev (set VITE_API_BASE_URL=http://localhost:8000 if needed)
Lint/build frontend: cd frontend && npm run lint / npm run build
Run full stack (Docker): docker compose up --build (frontend: http://localhost, backend: http://localhost:8000)

Coding Style & Naming Conventions

Python: 4-space indent, type hints where practical, snake_case for functions/modules, PascalCase for classes.
TypeScript/React: prefer functional components, PascalCase components, keep API URL configurable (see frontend/src/App.tsx).
Keep request/response models in services/api_gateway/app/schemas.py and persistence in services/api_gateway/app/models.py.

Testing Guidelines

Backend testing uses pytest (listed in requirements.txt). Add tests under tests/ as test_*.py and run pytest.
Smoke check: curl http://localhost:8000/healthz and a simple chat session via POST /api/chat/sessions.
Frontend has no unit test runner configured; use npm run build as a sanity check.

Commit & Pull Request Guidelines

Commit subjects commonly use prefixes like feat:, fix:, refactor:, docs:, chore:; keep the subject short and imperative.
PRs should include: what changed + why, steps to verify, and screenshots for UI changes.
Never commit secrets. Use .env.template as a starting point for local .env.

Read the full file on GitHub · 35 lines

Changes

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.

5d ago First seen · 35 lines · 660 tokens per session scan A 22a318e49507

Subscribe to this mod's changes

VentureBot AGENTS.md is an instructions file published in the GitHub repository gies-ai-experiments/VentureBot (5 stars, last pushed 2mo ago), licensed MIT. It adds 660 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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).

microsoft/vscode · 6,785 tokens

VentureBot AGENTS.md