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.
npx agentmods add instructions/orderlynetwork/orderly-mcp/agents-mdgit clone --depth 1 https://github.com/OrderlyNetwork/orderly-mcpWrote 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/orderlynetwork/orderly-mcp/agents-md)<a href="https://agentmods.dev/instructions/orderlynetwork/orderly-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/orderlynetwork/orderly-mcp/agents-md.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 | $0.07170 | $0.07170 |
| Opus 5 | $0.03585 | $0.03585 |
| Sonnet 5 | $0.01434 | $0.01434 |
| Haiku 4.5 | $0.00717 | $0.00717 |
Grade A, and why
orderly-mcp 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 3d 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 — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Orderly MCP Server
Project Overview
This is a Model Context Protocol (MCP) server that provides Orderly Network documentation and SDK patterns to AI assistants. It enables developers to query documentation, get code examples, and receive guidance on building trading UIs.
Key Technologies:
- TypeScript (ES modules)
- MCP SDK for tool/resource definitions
- Vitest for testing
- Yarn for package management
- ESLint + Prettier for code quality
Architecture
Entry Points:
src/index.ts- Stdio transport (for local MCP clients like Claude Desktop)src/http-server.ts- HTTP transport (for hosted deployments, Docker)src/server.ts- Shared MCP server logic (tools, resources, handlers)
Transports:
- Stdio: Default for local AI assistants, communicates via stdin/stdout
- HTTP: Stateless Streamable HTTP transport for remote access, runs on port 3000
- Docker: Runs HTTP mode by default with health checks
Tools (src/tools/*.ts):
searchDocs.ts- Unified fuzzy search overdocumentation.jsonand type-accurate SDK symbols (sdk-symbols.json). A singlesearch_orderly_docstool surfaces doc chunks and inline hook/type/component/function records (signature, params, returns, props, source) from the js-sdk symbol bundle.contracts.ts- Contract address lookupworkflows.ts- Workflow explanationsapiInfo.ts- API documentationindexerApi.ts- Indexer API documentationcomponentGuides.ts- Component building guidesorderlyOneApi.ts- Orderly One API documentationsvApi.ts- Strategy Vault API documentationpublicInfoApi.ts- Public Info API documentation
Data (src/data/*.json):
- Static JSON files with documentation, patterns, addresses
- Imported with
with { type: "json" }syntax - Read at runtime by tools
Resources (src/resources/index.ts):
- Handles URI-based resource requests
- Returns markdown or JSON content
Common Tasks
Build Project
yarn build
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.
- 3d ago First seen · 641 lines · 7,170 tokens per session scan A 1ed980d3b2a3
orderly-mcp AGENTS.md is an instructions file published in the GitHub repository OrderlyNetwork/orderly-mcp (8 stars, last pushed 20d ago), licensed MIT. It adds 7,170 tokens to every session, about $0.0358 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
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
VaultysClaw CLAUDE.md
Instructions for vaultys/VaultysClaw, covering claude.md, commands, development, demo / simulator and build.
plamen CLAUDE.md
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
behavioral-prediction-mcp AGENTS.md
Instructions for ChainAware/behavioral-prediction-mcp, covering chainaware subagent index, agent directory, chainaware-wallet-auditor, chainaware-fraud-detector and chainaware-rug-pull-detector.
chains-api CLAUDE.md
Instructions for Johnaverse/chains-api, covering claude.md — chains api, project overview, quick reference, architecture and tech stack.