Borrowing it
Nothing to install: this file belongs to amirkiarafiei/open-scholar-peer. 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/amirkiarafiei/open-scholar-peer/main/AGENTS.mdgit 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/instructions/amirkiarafiei/open-scholar-peer/agents-md)<a href="https://agentmods.dev/instructions/amirkiarafiei/open-scholar-peer/agents-md"><img src="https://agentmods.dev/badge/instructions/amirkiarafiei/open-scholar-peer/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/amirkiarafiei/open-scholar-peer/agents-md"><img src="https://agentmods.dev/badge/instructions/amirkiarafiei/open-scholar-peer/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 | $0.03133 | $0.03133 |
| Opus 5 | $0.01566 | $0.01566 |
| Sonnet 5 | $0.00627 | $0.00627 |
| Haiku 4.5 | $0.00313 | $0.00313 |
Grade A, and why
open-scholar-peer 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 10d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Open ScholarPeer
Init-style instructions for AI agents doing development on this repo. Read this first; depth lives in
docs/. (This file is for agents working on OSP itself — NOT the file end users get in their project. A separate user-facingAGENTS.mdis generated by the installers for tools that read project-root AGENTS.md (Copilot CLI, Codex, Kimi, Vibe, OpenCode, OpenHands), viascripts/merge_agents_md.shfromextensions/_shared/rules/osp-rules.md.)
What this project is
Open ScholarPeer (OSP) implements the paper "ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review" as a portable set of skills, slash commands, and an MCP server that install into a user's project across 14 AI tools (Claude Code, Cursor, Gemini CLI, Copilot CLI, Antigravity, Antigravity CLI, Codex CLI, Qwen Code, OpenCode, Junie, Kiro, Kimi Code, Mistral Vibe, OpenHands).
There is no runtime code. OSP is configuration-as-code. The library is the prompts and the sync infrastructure that keeps them consistent across tools.
Commands you will actually run
# After any edit under extensions/_shared/, regenerate adapters:
python3 scripts/sync_adapters.py
# Validate per-tool parity (must pass before any commit touching _shared/):
python3 scripts/test_parity.py
# Smoke-test all 14 installers in temp dirs (must pass before tagging release):
bash scripts/test_install.sh
# Syntax-check shell scripts:
for f in install.sh scripts/*.sh; do bash -n "$f" && echo " ✓ $f" || echo " ✗ $f"; done
# AST-check Python files (no formal linter configured):
python3 -c "import ast; [ast.parse(open(f).read()) for f in ['mcp-server/osp_mcp.py','scripts/sync_adapters.py','scripts/merge_mcp_config.py','scripts/test_parity.py']]"
# Run the MCP server standalone (debug mode):
cd mcp-server && python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && .venv/bin/python osp_mcp.py
Architecture (one paragraph)
extensions/_shared/ is the canonical source: 8 commands + 8 skills + rules + defaults + a manifest. scripts/sync_adapters.py regenerates 14 per-tool adapter directories under extensions/.{claude,cursor,gemini,agent,agents,github,junie,kiro,codex,kimi,qwen,vibe,opencode,openhands}/. Per-tool installers (scripts/install_*.sh) copy the adapter into the user's project, run init_brain.sh to scaffold .brain/, run init_mcp.sh to set up a self-contained Python venv at .open-scholar-peer/mcp/, and either auto-merge the MCP server into the tool's config (merge_mcp_config.py) or emit a paste-ready snippet for tools with TOML / global / non-standard configs. State during a review lives at <user-project>/.brain/ (gitignored).
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.
- 10d ago First seen · 188 lines · 3,133 tokens per session scan A 5f73233c9835
open-scholar-peer AGENTS.md is an instructions file published in the GitHub repository amirkiarafiei/open-scholar-peer (27 stars, last pushed 1mo ago), licensed MIT. It adds 3,133 tokens to every session, about $0.0157 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.