Borrowing it
Nothing to install: this file belongs to delta-exchange/delta-exchange-mcp. 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/delta-exchange/delta-exchange-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/delta-exchange/delta-exchange-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/delta-exchange/delta-exchange-mcp/agents-md)<a href="https://agentmods.dev/instructions/delta-exchange/delta-exchange-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/delta-exchange/delta-exchange-mcp/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/delta-exchange/delta-exchange-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/delta-exchange/delta-exchange-mcp/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 | $0.06314 | $0.06314 |
| Opus 5.5 | $0.02526 | $0.02526 |
| Sonnet 5.5 | $0.01263 | $0.01263 |
| Haiku 4.5 | $0.00631 | $0.00631 |
Grade A, and why
delta-exchange-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 21d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project in one line
MCP server (stdio only, built on the mcp SDK's MCPServer) that wraps Delta Exchange India's REST API as MCP tools — public market data unconditionally, plus authenticated account reads and trading mutations when DELTA_API_KEY/DELTA_API_SECRET are set. The API key's own permissions are the authorization boundary; the server applies no gate of its own (DEA-881).
Style
Don't add typing slop. In particular:
- Don't annotate pytest fixtures (
tmp_path,monkeypatch, etc.) — pytest discovers them by name, the annotation adds nothing. - Don't write
**kwargs: Any/-> Anyon internal test helpers. If the only honest type isAny, leave it off. - Use
Anyonly when it carries real information: a public boundary that genuinely accepts arbitrary JSON, a return type that is genuinely heterogeneous. Otherwise prefer the real type or no annotation at all. - Don't add
from typing import Anyjust to satisfy a redundant annotation.
Commands
uv sync # install deps (runtime + dev)
uv run pytest # run full suite (asyncio_mode=auto)
uv run pytest tests/test_market_tools.py::test_429_retries_then_succeeds # single test
uv run ruff check src tests scripts # lint
uv run ruff check --fix src tests scripts # lint + autofix
uv run delta-exchange-mcp # stdio (the only transport)
uv run python scripts/smoke.py # live smoke against DELTA_MCP_ENV
bash scripts/inspect.sh --cli --method tools/list
bash scripts/inspect.sh --cli --method tools/call --tool-name get_ticker --tool-arg symbol=BTCUSD
bash scripts/inspect.sh # Inspector web UI on :6274
Rebuilding the editable install after changing pyproject.toml or entry points: uv sync again — uv run caches the 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.
- 21d ago Changed · +7 lines · +542 tokens per session 7db9c372525a
- 1mo ago Changed · -6 lines · -536 tokens per session 20c95998044d
- 1mo ago First seen · 180 lines · 6,308 tokens per session scan A f383a1e1ceb6
delta-exchange-mcp AGENTS.md is an instructions file published in the GitHub repository delta-exchange/delta-exchange-mcp (16 stars, last pushed 2d ago), licensed MIT. It adds 6,314 tokens to every session, about $0.0253 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 2026-09-22.
delta-exchange-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| delta-exchange-mcp AGENTS.mddelta-exchange/delta-exchange-mcp | Instructions file | 16 | 2d ago | MIT | A | 6,314 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |