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/nytemodeonly/polyterm/agents-mdgit clone --depth 1 https://github.com/NYTEMODEONLY/polytermWhat 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 | $0.00407 | $0.00407 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
polyterm 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 yesterday.
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
Project Agent Rules
These instructions apply to all work in this repository.
Architecture Rule: No Monoliths
- Do not introduce monolithic files, modules, or command handlers.
- Prefer small, focused modules with clear single responsibilities.
- Keep features easy to edit, add, remove, and test in isolation.
- Split large changes into composable units (API layer, core logic, CLI/TUI wiring, tests).
- Favor explicit interfaces between modules over tightly coupled cross-module logic.
- When extending functionality, add or modify the smallest relevant module instead of expanding a central "god" file.
Change Quality Gate
Before finalizing substantial changes, verify:
- The code path can be understood without reading unrelated modules.
- A future contributor can replace/remove a feature without broad refactors.
- Tests are scoped to behavior of the touched module(s), not accidental implementation details.
Documentation Rule
- Keep
docs/README.mdaligned with the command, TUI, API, core, database, and utility modules that exist in the repo. - When adding or renaming a module under
polyterm/cli/commands,polyterm/tui/screens,polyterm/api,polyterm/core,polyterm/db, orpolyterm/utils, add or update the matching page underdocs/. - Do not leave generated placeholder docs in the published tree. Replace stubs with a clear overview, source path, data sources, verification notes, and related documentation links.
- For API-facing changes, document the current Polymarket endpoint contract and identifier requirements. Be explicit about Gamma market IDs, Gamma slugs, CLOB condition IDs, and CLOB token IDs.
- For CLI/TUI changes, document the exact command, shortcuts, options, output modes, and whether the workflow is view-only or can mutate local state.
- Run
./test_all_commands.sh,.venv/bin/python scripts/validate_docs.py, and focused tests for touched modules before committing documentation-sensitive changes.
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.
- yesterday First seen · 30 lines · 407 tokens per session scan A 29a3d126349d
polyterm AGENTS.md is an instructions file published in the GitHub repository NYTEMODEONLY/polyterm (355 stars, last pushed 4d ago), licensed MIT. It adds 407 tokens to every session, about $0.0020 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
kalshi-trading-bot-cli AGENTS.md
Instructions for OctagonAI/kalshi-trading-bot-cli, covering repository guidelines, project structure, build, test, and development commands, coding style & conventions and llm providers.
polymarket-tennis CLAUDE.md
Instructions for livetennisapi/polymarket-tennis: This package is the data layer for Polymarket tennis trading: market discovery (Polymarket Gamma API, keyless), market↔live-match matching (never guesses; returns None on ambiguity), and a joined LiveMarketView of market price vs live score.
kalshi-trading-bot-cli CLAUDE.md
Instructions for OctagonAI/kalshi-trading-bot-cli, covering claude.md and workflow.
simmer-sdk AGENTS.md
Instructions for SpartanLabsXyz/simmer-sdk, covering agents.md — simmer sdk, this repo is public, currency formatting, live is a constructor arg, not a per-trade flag and market discovery is recency-windowed.
polymarket-agent-mcp CLAUDE.md
Instructions for demwick/polymarket-agent-mcp, covering claude.md, build & test commands, architecture, entry point & mcp server and layers.
recuse CLAUDE.md
Instructions for xzycd/recuse, covering working in this repo, layout, commands, testing policy and things that will bite you.