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.
git clone --depth 1 https://github.com/amirkiarafiei/open-scholar-peerWrote 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/rules/amirkiarafiei/open-scholar-peer/osp-rules)<a href="https://agentmods.dev/rules/amirkiarafiei/open-scholar-peer/osp-rules"><img src="https://agentmods.dev/badge/rules/amirkiarafiei/open-scholar-peer/osp-rules/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/rules/amirkiarafiei/open-scholar-peer/osp-rules"><img src="https://agentmods.dev/badge/rules/amirkiarafiei/open-scholar-peer/osp-rules.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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
osp-rules 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open ScholarPeer — Always-On Rules
These rules apply automatically in any project where Open ScholarPeer is installed.
Brain protocol (apply on every invocation)
- Read
.brain/session.jsonfirst to understand current state. - Load only the artifacts in the active step's
reads:contract (seedocs/ARTIFACT_CONTRACTS.md). Do not load the full.brain/directory. - After completing a step, update
session.json: set the matchingphases.<name>block tocompleted, setcompleted_at, and updateresume_from. - Re-runs overwrite with a warning. If a step is already
completed, print one warning, then proceed.
Persona discipline
- Each numbered command (
/N-osp-*) activates exactly one persona skill (osp-<name>-agent). Do not blend personas. - The Q&A engine (
/5-osp-qa) uses two personas at once: Query Agent (main thread) and Answer Generator (subagent, or self-reflection on tools that lack subagents). - The orchestrator (
osp-orchestrator) never performs review work — it only routes.
Subagent vs self-reflection
- Prefer subagents for the Q&A engine on tools that support them (Claude Code, Cursor, Gemini CLI, Copilot CLI, Codex CLI, Qwen Code, OpenCode, Junie, Kiro, Kimi Code).
- Fall back to self-reflection with strict turn markers (
=== Query Agent === ... === END === === Answer Generator === ...) on tools without (or with only partial) subagent support: Antigravity, Mistral Vibe, OpenHands. - Self-reflection is a documented weaker substitute. See
KNOWN_LIMITATIONS.md.
User orientation (required on every phase invocation)
Before doing any work in a phase, print a short orientation block so the user always knows where they are:
── <Phase name> ──────────────────────────────────────────
What this phase does: <one sentence — the agent's role and why this step exists>
Reads: <list the key input files>
Writes: <list the key output files>
Effort: <rough estimate — "~2 min, ~N tool calls", etc.>
──────────────────────────────────────────────────────────
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 First seen · 63 lines · 868 tokens per session scan A fd4c71f15535
osp-rules is a cursor rule published in the GitHub repository amirkiarafiei/open-scholar-peer (27 stars, last pushed 1mo ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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 cursor rules, from other repositories
amplify-bootstrap
Amplify bootstrap — activates a structured scientific research workflow with 24 skills, 4 gates, and discipline enforcement. Loaded automatically for every session.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.