Borrowing it
Nothing to install: this file belongs to agent-next/polymarket-paper-trader. 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/agent-next/polymarket-paper-trader/main/AGENTS.mdgit clone --depth 1 https://github.com/agent-next/polymarket-paper-traderWrote 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/agent-next/polymarket-paper-trader/agents-md)<a href="https://agentmods.dev/instructions/agent-next/polymarket-paper-trader/agents-md"><img src="https://agentmods.dev/badge/instructions/agent-next/polymarket-paper-trader/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/agent-next/polymarket-paper-trader/agents-md"><img src="https://agentmods.dev/badge/instructions/agent-next/polymarket-paper-trader/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 | $0.01267 | $0.01267 |
| Opus 5.5 | $0.00507 | $0.00507 |
| Sonnet 5.5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
polymarket-paper-trader 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
polymarket-paper-trader — agent guide
Org standard: https://github.com/agent-next/.github/blob/main/AGENT-STANDARD.md Contribution and PR rules: CONTRIBUTING.md; security reports: SECURITY.md.
Purpose
Paper-trading simulator for Polymarket, built for AI agents (Python 3.10+, SQLite, Click CLI, MCP SDK 2.x). Public repo, actively maintained; the product ships to PyPI/ClawHub/MCP.
Org layering: a vertical (prediction-market domain) inside the agent-next org. Agent
runtimes consume it via MCP/CLI; model supply is not this repo's job (org agent-gateway
routes models) — this repo packages the domain logic, its benchmark, and the public arena.
Orient
git status --short,git branch --show-current,git worktree list,gh pr list --state open.- Currency: a local checkout can lag
origin/main; fetch and compare before trusting release numbers. - Module map, code conventions, testing rules: docs/architecture.md.
- Interfaces, live surfaces, release flow, verified upstream API facts, project state, known gaps: docs/agent-reference.md. Read it before touching API parsing or releases.
Layout
Four independent packages: the root polymarket-paper-trader (pm_trader/), benchmark/
(pm_benchmark/), leaderboard-client/ (pm_leaderboard_client/), and leaderboard-server/
(server/, depends on the root package and the client). Work on one package at a time; each
has its own tests and 100% coverage gate.
Setup
make setup creates .venv and installs all four packages editable with dev extras:
pip install -e ".[dev]" -e "benchmark[dev]" -e "leaderboard-client[dev]" -e "leaderboard-server[dev]".
Requires Python 3.10+ and pip.
Check
make check runs, per package, pytest tests/ -x -q -m "not live" with --cov-fail-under=100,
using the venv's Python (no version pin). CI (.github/workflows/test.yml + toolkit.yml)
runs coverage on Python 3.13 and the 3.10-3.12 matrix without coverage.
Narrow variant: run the same pytest command inside the one package directory you touched.
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.
- 9d ago Changed · -51 lines · -906 tokens per session f7a7f6069533
- 22d ago Changed · +4 lines · +98 tokens per session 9b3a249d8d3b
- 25d ago Changed · +2 lines · +35 tokens per session 34e5e97408fe
- 27d ago Changed · +4 lines · +83 tokens per session 1036030d2682
- 28d ago Changed · +31 lines · +488 tokens per session 34750d51b53f
- 29d ago Changed · +76 lines · +1,260 tokens per session 91cd38b24799
- 1mo ago First seen · 20 lines · 209 tokens per session scan A a06ca1a6eaf6
polymarket-paper-trader AGENTS.md is an instructions file published in the GitHub repository agent-next/polymarket-paper-trader (492 stars, last pushed 4d ago), licensed MIT. It adds 1,267 tokens to every session, about $0.0051 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 2026-09-23.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).