Borrowing it
Nothing to install: this file belongs to tradecatlabs/tradecat-public. 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/tradecatlabs/tradecat-public/develop/AGENTS.mdgit clone --depth 1 https://github.com/tradecatlabs/tradecat-publicWrote 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/tradecatlabs/tradecat-public/agents-md)<a href="https://agentmods.dev/instructions/tradecatlabs/tradecat-public/agents-md"><img src="https://agentmods.dev/badge/instructions/tradecatlabs/tradecat-public/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/tradecatlabs/tradecat-public/agents-md"><img src="https://agentmods.dev/badge/instructions/tradecatlabs/tradecat-public/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 | $0.03236 | $0.03236 |
| Opus 5 | $0.01618 | $0.01618 |
| Sonnet 5 | $0.00647 | $0.00647 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
tradecat-public 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 9d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tradecat-public Agent 操作手册
本文件作用域：tradecat-public/**。它是 AI 编码/自动化 Agent 的作业说明书。执行任务时以仓库事实为准：先读代码和配置，再改文件；不确定就写 TODO，不允许猜。
Mission & Scope
TradeCat Public 的使命是：Agent 交易员同步公开在线表格作为信号源，自主补齐 Binance public/read-only market context，生成 thesis，再由 TradeCat 执行 schema 审计、paper/watch、账本、风控拒绝、报告和可复现审计。
仓库身份以 tradecat-public 为准；GitHub remote 为 tukuaiai/tradecat-public。Agent 不得把它当成旧私有 TradeCat 运行态或实盘 executor。
允许做：
- 修改
src/tradecat_sources/的公开在线表格信号源适配。 - 修改
src/tradecat_auto/的 Agent context 审计、paper/watch、ledger、风控、报告和本地运行态逻辑。 - 修改
contracts/、resources/、tests/、scripts/、docs/、skills/tradecat-public/中与任务直接相关的契约、资源、测试、脚本和文档。 - 运行 public-readonly 命令、本地 paper/watch 命令和验证门禁。
禁止做：
- 禁止连接或写入 TradeCat 服务端 PostgreSQL。
- 禁止依赖内部
apps/sheets实现细节；只能依赖公开在线表格 CSV 契约。 - 禁止提交缓存、运行日志、账本、Google key、Binance key、secret、
.env、私钥、真实账户输出或真实订单日志。 - 禁止读取 Binance key/secret、listen key、账户、余额、真实持仓或订单。
- 禁止签名请求，禁止调用真实下单、撤单、改杠杆、改保证金或账户私有接口。
- 禁止恢复旧本地 TUI、安装器、watchdog、缓存浏览器和
project/根目录。 - 禁止在缺 Agent sizing/leverage/exits 时硬编码默认仓位、默认杠杆、默认止损止盈或默认持仓时长。
敏感或本地路径：
.runtime/、.tradecat/、.venv/、.hermes/、.tools/、project/、tasks/只属于本机运行态或开发态，必须保持 ignored。skills/tradecat-public/agents/manifest.json是 Agent/Hermes 机器主契约。- TODO: GitHub 平台分支保护配置无法从仓库文件确认；需要仓库管理员核查 GitHub Settings。
Golden Path
标准执行路径：
git status --short --branch- 阅读任务相关文件、
README.md、本文件、skills/tradecat-public/agents/manifest.json和相关contracts/。 - 安装或确认开发依赖：
python3 -m pip install -c constraints.txt -e ".[dev]" - 先跑针对性测试或只读命令复现问题。
- 做最小必要修改；不做顺手重构。
- 同步测试、schema、manifest、README/AGENTS/docs/references。
- 运行必须门禁。
- 汇报改动、验证、剩余风险和 git 状态；未获明确要求不得 push。
Must-Run Commands
安装：
python3 -m pip install -c constraints.txt -e ".[dev]"
只读入口：
python3 scripts/request.py --datasets --format json
python3 scripts/request.py signal_flow --format json --limit 5
python3 scripts/request.py anomaly_panel --format json --limit 0
bash scripts/binance-public-snapshot.sh --symbols BTCUSDT,ETHUSDT --json
bash scripts/binance-public-bundle.sh --symbols BTCUSDT,ETHUSDT --json
bash scripts/run-tradecat.sh agent-market-context --symbol BTCUSDT --json
bash scripts/run-tradecat.sh soft-layer --json
bash scripts/start-auto-paper.sh status --json
bash scripts/run-tradecat.sh latest-cycle --json
bash scripts/run-tradecat.sh latest-decision --json
bash scripts/run-tradecat.sh strategy-review --ledger-path .runtime/auto-paper/paper_ledger.json --archive-path .runtime/auto-paper/cycles.jsonl --json
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.
- 9d ago First seen · 222 lines · 3,236 tokens per session scan A 0ea55be3ed81
tradecat-public AGENTS.md is an instructions file published in the GitHub repository tradecatlabs/tradecat-public (956 stars, last pushed today), licensed MIT. It adds 3,236 tokens to every session, about $0.0162 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
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.
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).
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).
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.
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.