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/openraiser/paperfit/paperfitgit clone --depth 1 https://github.com/OpenRaiser/PaperFitWhat 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 | $0.00000 | $0.00469 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
paperfit 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 3d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PaperFit Rule
Use PaperFit when working on a LaTeX paper that needs visual typesetting optimization.
Product Rules
- Work from the paper project root.
- Treat PaperFit as a natural-language agent system, not a CLI-first workflow.
- Users should describe goals directly, such as layout analysis, full repair, template migration, page-budget adjustment, or visual-only inspection.
- Automatically infer the closest PaperFit workflow from the user's request before asking them for low-level PaperFit command syntax.
Execution Rules
- Use the
paperfitCLI, runtime, and scripts as the internal execution layer. - Prefer
paperfit runtime --state data/state.json run-round main.tex --template <TEMPLATE> --target-pages <N>for the main closed loop. - Use
paperfit renderandpaperfit run scripts/...only for targeted debugging, staged execution, or recovery. - Do not require the user to manually type internal PaperFit commands in the normal product path.
- During long PaperFit runs, report progress proactively instead of staying silent.
- Prefer self-recovery in recoverable failures; only ask the user to act when environment, permission, or ambiguity issues block execution.
- Keep user-facing explanations centered on results, visual defects, repair strategy, and residual risks.
Layout Rules
- Do not use
\resizeboxor\scaleboxas brute-force table shrinking. - Prefer full-width or full-column table layouts that preserve readability and alignment.
- Do not change the template font packages or the visual font appearance of body text and tables during repair.
- Confirm fixes against rendered page images, not source-only inspection.
- Treat visual results as the primary acceptance signal; logs and source are supporting evidence.
- Keep semantic edits minimal and do not alter academic claims, results, or citations.
- Do not silently delete figures, tables, captions, or labels to improve layout.
Installed Assets
- Global PaperFit skills live under
~/.cursor/skills/paperfit/. - This rule file is project-local and should live at
.cursor/rules/paperfit.mdcinside the paper repository.
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.
- 3d ago First seen · 43 lines · 0 tokens per session scan A 937ea47225a9
paperfit is a cursor rule published in the GitHub repository OpenRaiser/PaperFit (330 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 469 tokens. 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 cursor rules, from other repositories
fortran
Modern Fortran rules for scientific computing, modules, explicit interfaces, kind parameters, memory safety, and testing.
workers-config
Wrangler config rules - secrets vs vars, generated types, RPC typing, fail-closed expectations.
type-inference
Derive TypeScript types from Zod schemas - no hand-written interfaces for wire shapes.
general
You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.
turborepo
Turbo query graph primitives and signed remote-cache key provisioning.
workers-cache
Workers Cache - Cache-Control, gateway exports cache off, RPC vs fetch.