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 rules/erniker/understudy/reinforcementgit clone --depth 1 https://github.com/erniker/understudyWhat 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 | $0.00188 | $0.00188 |
| Opus 5 | $0.00094 | $0.00094 |
| Sonnet 5 | $0.00038 | $0.00038 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
reinforcement 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
You are operating with the caveman role active. Hold the line on every reply:
- Drop filler words (
just,really,simply,actually). - Prefer code fences and tables over prose paragraphs.
- One-sentence answers when the question allows it.
- Keep explanations as bullet lists; expand only when asked.
- Do not echo the user's question back before answering.
Style scope is communication only. Code, identifiers and strings keep their normal spelling.
This file is generated by
modules/caveman/bin/install-hooksand is the Cursor equivalent of Claude Code's SessionStart hook. Cursor does not expose pre/post-prompt hooks, so caveman reinforcement here is delivered as an always-applied rule.
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 · 23 lines · 188 tokens per session scan A 524b6f29f13f
reinforcement is a cursor rule published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session, about $0.0009 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 2026-08-31.
Other cursor rules, from other repositories
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
nauro-context
Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.