QuantDinger is a self-hosted AI trading platform that lets operators research markets, write Python strategies, test them, and run paper or live trades while monitoring results. Independent traders, strategy authors, and small teams use it to operate trading services across crypto, stocks, and forex, with user management and billing features for multi-tenant deployments.
Borrowing it
Nothing to install: this file belongs to OpenByteInc/QuantDinger. 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/OpenByteInc/QuantDinger/main/AGENTS.mdgit clone --depth 1 https://github.com/OpenByteInc/QuantDingerWrote 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/openbyteinc/quantdinger/agents-md)<a href="https://agentmods.dev/instructions/openbyteinc/quantdinger/agents-md"><img src="https://agentmods.dev/badge/instructions/openbyteinc/quantdinger/agents-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/openbyteinc/quantdinger/agents-md"><img src="https://agentmods.dev/badge/instructions/openbyteinc/quantdinger/agents-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 | $0.00763 | $0.00763 |
| Opus 5.5 | $0.00305 | $0.00305 |
| Sonnet 5.5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
QuantDinger AGENTS.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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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*.ymlandscripts/: deployment topology and lifecycle tooling.- Frontend source is maintained outside this repository. The prebuilt frontend image is configured by the
frontendservice indocker-compose.yml.
Read by task
Read only the documentation relevant to the change:
- Agent Gateway or MCP: Agent documentation, Agent OpenAPI, and MCP package documentation.
- Strategy API, backtests, or trading behavior: Strategy development guide and live-trading safety.
- Runtime ownership, concurrency, Kafka, workers, or durable state: architecture index and the task-specific document it links.
- HTTP contracts: API conventions and the applicable OpenAPI document.
- Installation or operations: the root README 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/v1is the Agent Gateway boundary. Updatedocs/agent/agent-openapi.jsonand 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.
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.
- 1mo ago First seen · 47 lines · 763 tokens per session scan A e382a8d24af9
QuantDinger AGENTS.md is an instructions file published in the GitHub repository OpenByteInc/QuantDinger (13,551 stars, last pushed yesterday), licensed Apache-2.0. It adds 763 tokens to every session, about $0.0031 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 2026-10-01.
QuantDinger AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| QuantDinger AGENTS.mdOpenByteInc/QuantDinger | Instructions file | 14k | yesterday | Apache-2.0 | A | 763 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |