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/jun229/tm-mcp-server/claude-mdgit clone --depth 1 https://github.com/jun229/tm-mcp-serverWrote 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/jun229/tm-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/jun229/tm-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jun229/tm-mcp-server/claude-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 | $0.00795 | $0.00795 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
tm-mcp-server CLAUDE.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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project overview
MCP (Model Context Protocol) server for True Markets. Gives AI agents native crypto trading tools instead of shelling out to tm CLI via bash.
Architecture
- Transport: stdio (agents spawn this as a subprocess)
- Auth: Reads credentials from
~/.config/truemarkets/(shared with thetmCLI) - API: Wraps the True Markets DeFi Gateway at
api.truemarkets.co - Signing: Turnkey P256 ECDSA via
src/services/signer.ts(needs@turnkey/api-key-stamperfor production)
Key design decision: quote caching
The CLI's --dry-run and --force fetch separate quotes, so agents decide on one price but execute at another. This server caches quotes for 60 seconds — tm_get_quote returns a quote_id, and tm_execute_trade signs and submits the same cached quote.
Tools (8 total)
Read-only: tm_get_price, tm_get_balances, tm_list_assets, tm_get_profile
Trading: tm_get_quote, tm_execute_trade, tm_prepare_transfer, tm_execute_transfer
Build and test
npm install
npm run build # tsc → dist/
npm start # runs dist/index.js (stdio transport)
Verify MCP handshake:
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}}}' | node dist/index.js 2>/dev/null
File structure
src/
├── index.ts # Entry point, McpServer + stdio transport
├── constants.ts # API_HOST, API_VERSION, config paths
├── types.ts # Chain, OrderSide, USDC addresses, helpers
├── services/
│ ├── auth.ts # TokenManager — loads JWT + API key from disk
│ ├── api-client.ts # HTTP client for all 8 DeFi Gateway endpoints
│ └── signer.ts # Turnkey P256 payload signing (TODO: use @turnkey/api-key-stamper)
└── tools/
├── read.ts # Read-only tools (price, balances, assets, profile)
└── trade.ts # Trading tools (quote, execute, transfer) + quote cache
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 · 68 lines · 795 tokens per session scan A 08412083d5cf
tm-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jun229/tm-mcp-server (0 stars, last pushed 5mo ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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
mercato-dapp AGENTS.md
Instructions for mercato-supply-chain/mercato-dapp, covering mercato — agent guide, quick facts, documentation map, domain glossary and user roles.
lightning-enable-mcp CLAUDE.md
Instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.
x402-stellar-kit AGENTS.md
AGENTS.md instructions for CodeStrux/x402-stellar-kit, covering working with x402-stellar-kit, the one invariant, production seams, bootstrapping accounts across a custody boundary and add x402 to an existing api.
ai-oracle-skills CLAUDE.md
Instructions for APRO-com/ai-oracle-skills, covering claude.md, project overview, api essentials, testing and code generation verification.
cryptopilot-mcp CLAUDE.md
Claude Code instructions for cryptopilot-tools/cryptopilot-mcp, covering claude.md, project, stack, architecture and mcp tools (5).
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.