Skip to content
Agentmart
Submit a tool

AGENTS.md · OpenByteInc/QuantDinger

AGENTS.md from OpenByteInc/QuantDinger: 47 lines covering Repository map, Read by task, Architecture and contract invariants, Safety and repository hygiene…

Template by OpenByteInc

IndexedApache-2.0★ 13,079
Write a review

Chalk Labs

Need help deploying AGENTS.md · OpenByteInc/QuantDinger?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/OpenByteInc/QuantDinger/main/AGENTS.md -o AGENTS.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The AGENTS.md file that OpenByteInc/QuantDinger (13,076 stars) keeps for coding agents. It has 47 lines in 5 sections: Repository map; Read by task; Architecture and contract invariants; Safety and repository hygiene; Verification. Use it as a model for your own project's instructions.

Use cases: prompt-engineering, code-generation

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.

For
Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
Length
47 lines
File
AGENTS.md

Sections

  1. Repository map
  2. Read by task
  3. Architecture and contract invariants
  4. Safety and repository hygiene
  5. Verification

First lines (shown under the repo's Apache-2.0 license)

# QuantDinger Repository Instructions

This is the canonical instruction file for coding agents working in this repository. Keep tool-specific entrypoints thin and do not duplicate these rules elsewhere.

## Repository map

- `backend_api_python/`: Flask API, services, trading runtime, migrations, and backend tests.
- `mcp_server/`: the tenant-scoped MCP client/server package backed by QuantDinger APIs.
- `docs/`: product, architecture, deployment, API, Agent Gateway, and trading documentation.
- `docker-compose*.yml` and `scripts/`: deployment topology and lifecycle tooling.
- Frontend source is maintained outside this repository. The prebuilt frontend image is configured by the `frontend` service in `docker-compose.yml`.

## Read by task

Read only the documentation relevant to the change:

- Agent Gateway or MCP: [Agent documentation](docs/agent/README.md), [Agent OpenAPI](docs/agent/agent-openapi.json), and [MCP package documentation](mcp_server/README.md).
- Strategy API, backtests, or trading behavior: [Strategy development guide](docs/trading/STRATEGY_DEV_GUIDE.md) and [live-trading safety](docs/trading/LIVE_TRADING_SAFETY.md).
- Runtime ownership, concurrency, Kafka, workers, or durable state: [architecture index](docs/architecture/README.md) and the task-specific document it links.
- HTTP contracts: [API conventions](docs/architecture/API_CONVENTIONS.md) and the applicable OpenAPI document.
- Installation or operations: the root [README](README.md) and the applicable guide under `docs/deployment/`.

## Architecture and contract invariants

- Preserve the process ownership documented in the architecture index. Do not move persistent trading loops into the HTTP backend or let evaluator processes submit exchange orders directly.
- PostgreSQL is the durable source of truth. Kafka transports versioned events; Redis cache data is evictable, while the jobs Redis has a separate durability role. Do not silently substitute one for another.
- Keep tenant isolation, idempotency, leases, fencing, and audit behavior intact when changing distributed or trading workflows.
- `/api/agent/v1` is the Agent Gateway boundary. Update `docs/agent/agent-openapi.json` and its alignment tests whenever that HTTP contract changes.
- MCP capabilities must retain the same authentication, scopes, idempotency, limits, and live-trading safeguards as the backing API.

## Safety and repository hygiene

- Never commit real secrets, production `.env` files, API keys, or database passwords. Use `.env.example` and placeholders.
- Do not weaken live-trading safeguards or bypass explicit authorization and human review unless the user requests and scopes that change.
- Do not add upgrade-time data rewrites for one-off local cleanup. Use an explicit, reviewed migration only when shipped user data must change.
- Preserve unrelated working-tree changes.
- Use English for source-code comments. Keep user-facing application copy in the existing localization system rather than hardcoding it in source files.
- Keep machine-readable contracts and identifiers in English. When a human guide has English and `_CN` editions, update both when the change affects both audiences.

## Verification

- Run focused backend tests from `backend_api_python/` with `python -m pytest tests/<test_file>.py -q`.
- Agent contract coverage lives in `backend_api_python/tests/test_ai_agent_contract_alignment.py` and related `test_agent_*.py` files.
- MCP tests live in `mcp_server/tests/`.
- Validate Compose changes with `docker compose config --quiet` before exercising the affected services.
- Match verification depth to risk; trading, migrations, tenancy, and distributed ownership require targeted regression tests.

Signals

Stars
13,079
Forks
2,662
Open issues
25
Last commit (this folder)
Sep 30, 2026 (1 month ago)
Last release
Oct 24, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get AGENTS.md · OpenByteInc/QuantDinger running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying AGENTS.md · OpenByteInc/QuantDinger?

CallGet help
Cite this page

AGENTS.md · OpenByteInc/QuantDinger. Agent Mart. https://agentmart.dev/templates/openbyteinc-quantdinger-agents-md (last updated 2026-10-24)