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/ferdousbhai/tasty-agent/agents-mdgit clone --depth 1 https://github.com/ferdousbhai/tasty-agentWrote 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/ferdousbhai/tasty-agent/agents-md)<a href="https://agentmods.dev/instructions/ferdousbhai/tasty-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/ferdousbhai/tasty-agent/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 5.1 | $0.00325 | $0.00325 |
| Opus 5 | $0.00162 | $0.00162 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
tasty-agent 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 2d 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.
What it actually says
tasty-agent
MCP server for Tastytrade account data, market data, watchlists, and order workflows.
Code index
tasty_agent/server.py— FastMCP tools, transport entry point, rate limiting, and orchestrationtasty_agent/orders.py— instrument resolution, leg construction, quote-derived pricing, tick rounding, and budget sizingtasty_agent/core.py— session and account lifecycletasty_agent/market_data.py— DXLink quotes and Greekstasty_agent/account_helpers.py— compact account, balance, position, order, and transaction outputtasty_agent/watchlists.py— watchlist operationstests/— unit and credential-gated integration testsexamples/— local clients and deployment examplescommands/portfolio.md— Claude Code command surfaceskills/trading/SKILL.md— Claude Code trading skill
Boundaries
- All SDK calls share the existing two-requests-per-second limiter.
- Option chains use the existing 24-hour cache; tests that depend on chain changes must invalidate it explicitly.
- Order pricing must use the helpers in
orders.py; preserve signed debit/credit semantics and broker dry-run safety. - Keep MCP output compact and never replace selected projections with full SDK payloads.
Commands
uv run pytest
uv run ruff check .
uv run ruff format --check .
uv run pyright
Credential-gated tests and live brokerage calls require explicit authorization.
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.
- 2d ago Changed · +1 lines · -36 tokens per session 507a46ffda50
- 6d ago First seen · 34 lines · 361 tokens per session scan A 6d2dda7c76d9
tasty-agent AGENTS.md is an instructions file published in the GitHub repository ferdousbhai/tasty-agent (84 stars, last pushed 3d ago), licensed MIT. It adds 325 tokens to every session, about $0.0016 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
quantdata-plugin GEMINI.md
Gemini CLI instructions for celineycn/quantdata-plugin, covering quant data, authentication and pricing, resolving what the user said into a symbol, get /v1/weis/{symbol} — weis wave volume-price events and where this fails — say so out loud.
tradememory-protocol AGENTS.md
Instructions for mnemox-ai/tradememory-protocol, covering tradememory protocol — agent context, project rules, recent changes and current status.
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
polymarket-alpha-bot CLAUDE.md
Instructions for chainstacklabs/polymarket-alpha-bot, covering claude.md, commands, development, pipeline and seed data.
ohlcv CLAUDE.md
Claude Code instructions for Mario-SO/ohlcv, covering claude.md, project overview, build and development commands, core commands and build the library and demo.
robinhood-mcp AGENTS.md
Instructions for verygoodplugins/robinhood-mcp, covering agents.md, project overview, read-only is a hard invariant, build & development and install with dev dependencies (editable).