Borrowing it
Nothing to install: this file belongs to up2itnow0822/ReadyTrader-Stocks. 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/up2itnow0822/ReadyTrader-Stocks/main/AGENTS.mdgit clone --depth 1 https://github.com/up2itnow0822/ReadyTrader-StocksWrote 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/up2itnow0822/readytrader-stocks/agents-md)<a href="https://agentmods.dev/instructions/up2itnow0822/readytrader-stocks/agents-md"><img src="https://agentmods.dev/badge/instructions/up2itnow0822/readytrader-stocks/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/up2itnow0822/readytrader-stocks/agents-md"><img src="https://agentmods.dev/badge/instructions/up2itnow0822/readytrader-stocks/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 | $0.01372 | $0.01372 |
| Opus 5.5 | $0.00549 | $0.00549 |
| Sonnet 5.5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
ReadyTrader-Stocks 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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReadyTrader-Stocks
Root AGENTS.md (DOX rail).
Purpose
A stdio MCP server (app/main.py, 20 tools) that lets an AI agent research US stocks, paper trade
in a local ledger, and optionally place live brokerage orders behind a Risk Guardian, an operator
policy and a kill switch; plus an approval/dashboard API (app/api_server.py) and a Next.js
dashboard (frontend/).
Ownership
app/: MCP tool surface (app/tools/), settings (app/core/config.py), the approval API.core/: pure rules (risk, Falling Knifemarket_guard, policy, paper ledger, backtest).execution/: brokerage connectors and the approval store;marketdata/,intelligence/: data sources.common/: shared helpers (common/switches.py,common/paths.py).research/falling_knife/: the study behinddocs/FALLING_KNIFE.md; nothing imports it._deprecated/: history only, never shipped.configs/: copy/paste MCP client configs, each in its client's own format (Agent Zero:agent_zero.mcp.json, the{"mcpServers": ...}JSON for Settings → MCP/A2A → External MCP Servers);tests/test_configs.pykeeps them and the README's examples in step.
Local Contracts
- Fail closed. Safety switches are parsed with
common/switches.py: protections stay on unless explicitlyfalse/0/no/off;LIVE_TRADING_ENABLEDneeds exactlytrue; the kill switch halts on any value but empty/off; an unknownEXECUTION_APPROVAL_MODErequires approval; an unreadable limit refuses live orders. Brokerage connectors default to paper/sandbox accounts. - Every live order passes
pre_trade_checkandlive_order_refusalwhen placed or proposed, and again at execution (including/api/approve-trade); a proposal executes only in the mode (paper/live) it was made in. - Risk rules judge the exposure an order adds (from the paper ledger or the brokerage's positions): selling out of a position is never sized as new exposure; an order that adds exposure and cannot be priced or sized is refused; unknown live positions count as new exposure.
- Orders are valued at the market price (a limit at the higher of limit and market), never at a
price the caller supplies alone; a market order's
priceis dropped before it can size, propose or reach a brokerage. Symbols are normalised (strip, upper case) once, inplace_stock_order; a/is refused, and in paper mode so is a ticker spelled like the ledger's cash (USD). - Paper loss limits (
core/paper.py get_risk_metrics) read a time-weighted performance index: deposits (valued when made;deposit_paper_fundsrefuses shares it cannot price) are neither gains nor losses; holdings are marked to the latest quote before every check; the daily baseline is the previous UTC day's last snapshot, else the day-open mark. Live orders report the daily-loss and drawdown rules ininactive_rules. - The approval API:
API_OPERATOR_TOKEN(API process only) gates every/api/call but/api/healththrough therequire_operatordependency of theoperator_apirouter (never a path check in a middleware: the URL path can differ from the routed path); CORS is added after therequest_contextmiddleware so it wraps every answer. It is required to approve live proposals (the agent holds theconfirm_token); every response carriesX-Request-IDand security headers; errors never echo exception text. - Tools answer
{"ok": true, "data"}or{"ok": false, "error": {"code", "message", "data"}}; a source that cannot answer is an error, never a payload. New codes go indocs/ERRORS.md. - A price is finite and positive or it is no price: provider rows without one are dropped
(
marketdata/exchange_provider._priced_rows), orders value only real prices (_real_price), and the paper engine refuses a non-finite price, amount or balance before it writes (NaN compares false against every limit). - Default data files live in
<repo>/data/viacommon/paths.data_path(never the working directory);READYTRADER_DATA_DIRand each*_PATHvariable override. - Every variable the code reads is in
env.example, with no inline comments or placeholder keys. - Nothing waits at the broker: an Alpaca order is sent only while the market is open
(
market_closed_reason; elsemarket_closed), asIOC(fractional market ordersDAY, fractional limits refused), and read back for what filled, because the Guardian judges an order at the moment it is placed; the other connectors' resting limits are documented, never counted. - Numeric MCP tool parameters use
app/tools/params.py(Number,Integer): booleans are refused. - In live mode the operator switches answer first (order tools and approval, before a proposal is
consumed); every well-formed order request is audited (
trade_start). - Docker: the image runs as the unprivileged
readytraderuser;.dockerignorepatterns are**/(a bare pattern matches only at the context root) and keep every.env*, key file and database out. - Docs describe only what runs: after changing a tool, run
python tools/generate_tool_docs.pyand update README /docs/in the same change.
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.
- 10d ago First seen · 79 lines · 1,372 tokens per session scan A 4c8bcc978559
ReadyTrader-Stocks AGENTS.md is an instructions file published in the GitHub repository up2itnow0822/ReadyTrader-Stocks (0 stars, last pushed 10d ago), licensed MIT. It adds 1,372 tokens to every session, about $0.0055 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 2026-10-11.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.