Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/instructions/vanszs/bybit_autotrade/copilot-instructions)<a href="https://agentmods.dev/instructions/vanszs/bybit_autotrade/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/vanszs/bybit_autotrade/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01235 | $0.01235 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
Bybit_AutoTrade copilot-instructions.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 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.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bybit Trading Bot - AI Agent Instructions
Architecture Overview
This is a unified Bybit V5 trading bot with Telegram interface, LLM integration, and MCP server capabilities. The architecture follows a public-first design with clear private endpoint gating.
Core Components
src/main.py: Single unified entrypoint withEnhancedBybitBotclass - handle Telegram commands and natural language queriessrc/bybit_client.py: Bybit V5 REST client with authentication, simulation modes, and strict public/private endpoint separationsrc/llm.py: OpenAI-compatible client (default: Novita GPT-OSS) with error handling for balance issuessrc/config.py: Environment-based configuration with public_only mode toggletools/mcp_server.py: Optional MCP server for external AI tool integration
Key Architectural Decisions
Public-First Design: Bot defaults to BYBIT_PUBLIC_ONLY=true mode. Private endpoints require explicit configuration and show clear guidance when unavailable.
LLM Intent Analysis: Natural language queries go through analyze_user_intent() which uses comprehensive API documentation context to route to appropriate Bybit endpoints.
Dual Authentication Modes:
- Public-only: Market data, server time, tickers (no API keys needed)
- Full mode: Wallet balance, positions, trading (requires
BYBIT_API_KEY/BYBIT_API_SECRET)
Essential Editing Patterns
When Editing Existing Files (DO NOT CREATE NEW FILES)
Main.py Pattern: Always edit src/main.py directly. DO NOT create enhanced_main.py, main_complete.py, or similar variants.
Single Source of Truth: Update existing files rather than creating duplicates. The codebase follows this principle strictly.
API Client Extension Pattern
# In bybit_client.py - Add new endpoints following this pattern:
async def new_endpoint(self, category: str, symbol: str) -> Dict[str, Any]:
if self.simulation_mode:
return self._simulate_endpoint_data(symbol)
if self._client is None:
return {"retCode": 10002, "retMsg": "Client not initialized", "result": {}}
# Implementation with proper error handling
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 · 142 lines · 1,235 tokens per session scan A 77a607d63dc7
Bybit_AutoTrade copilot-instructions.md is an instructions file published in the GitHub repository Vanszs/Bybit_AutoTrade (0 stars, last pushed 11mo ago), licensed MIT. It adds 1,235 tokens to every session, about $0.0062 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 2026-08-31.
Other instructions, from other repositories
gmgn-skills CLAUDE.md
Claude Code instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
mercato-dapp AGENTS.md
Instructions for mercato-supply-chain/mercato-dapp, covering mercato — agent guide, quick facts, documentation map, domain glossary and user roles.
coingecko-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/coingecko-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
gensyn-delphi-skills CLAUDE.md
Instructions for gensyn-ai/gensyn-delphi-skills, a project described as: Skills for agents to view markets and place trades on Gensyn's Delphi prediction markets.
x402-stellar-kit CLAUDE.md
Claude Code instructions for CodeStrux/x402-stellar-kit, a project described as: x402 payment primitives for Stellar: intent binding, a deterministic policy engine, a pluggable approver, and an agent surface. Apache-2.0.
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).