open-scholar-peer: Instructions file for Claude Code

CLAUDE.md

open-scholar-peer CLAUDE.md is an instructions file for Claude Code from amirkiarafiei/open-scholar-peer. It costs 1,716 tokens per session, scanned A, original, MIT.

Repository instructions for using kiacontext, a set of Markdown files that records project decisions, history, current work, and constraints for future coding sessions. It tells an agent which context files to read and how to keep them honest.

In plain words
What is it for?
Use it when starting work in the repository, reading its context map, recording decisions, and deciding when to update project notes.
Why use it?
It reduces repeated work and prevents agents from reversing deliberate decisions or forgetting why unusual code exists. It gives project memory that cannot be recovered from source code alone.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is amirkiarafiei/open-scholar-peer's own configuration. It tells Claude Code how to work on open-scholar-peer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-scholar-peer configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/amirkiarafiei/open-scholar-peer/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/amirkiarafiei/open-scholar-peer

Made for: Claude Code.

Wrote 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.

agentmods badge for open-scholar-peer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amirkiarafiei/open-scholar-peer/claude-md/github.svg)](https://agentmods.dev/instructions/amirkiarafiei/open-scholar-peer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/amirkiarafiei/open-scholar-peer/claude-md"><img src="https://agentmods.dev/badge/instructions/amirkiarafiei/open-scholar-peer/claude-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.

agentmods 80×15 button for open-scholar-peer CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/amirkiarafiei/open-scholar-peer/claude-md"><img src="https://agentmods.dev/badge/instructions/amirkiarafiei/open-scholar-peer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,716 This file is loaded in full into every session.
When invoked 1,716 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01716 $0.01716
Opus 5.5 $0.00686 $0.00686
Sonnet 5.5 $0.00343 $0.00343
Haiku 4.5 $0.00172 $0.00172

Measured 1mo ago against content hash befdc0926196, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

open-scholar-peer CLAUDE.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 1mo 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.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kiacontext — this project's memory. Read this before you start work.

This repository carries a folder called kia-context/. It is a small set of Markdown files holding what a reader of the code cannot see: what is being built right now, what was already decided and why, what was tried and rejected, and what must never change. The layout is a reusable harness called kiacontext; everything inside it is specific to this project.

👉 Start by reading kia-context/INDEX.md.

It is the map of every other file — one minute of reading, and nothing below makes proper sense without it. Read it before your first substantial action in a session, not when you get stuck.

Why this exists. You start every session with no memory of the last one. The code can tell you what the system does; it can never tell you why it is that way, what was already attempted and abandoned, or which awkward-looking part is deliberate and must not be "improved". Without that, settled arguments get re-run, decisions get quietly reversed, and work is redone. These files are the part of the project that survives between sessions.

They are authoritative. Where the code and a spec disagree, that is a finding to raise with the human — not a document to ignore.

You write these files. The human decides what goes in them. Every file under kia-context/ is written by an agent, out of a conversation — nobody maintains them by hand. Your job is to keep them true.

How to use them.

  • Before proposing or building anything: specs/MANIFESTO.md for the boundary you may not cross, and the active logs/BRAINSTORM.md to check whether your idea was already considered and rejected.
  • Before touching anything structural: specs/ARCHITECTURE.md.
  • Every session: logs/PROGRESS.md holds the current milestone, its deliverables and their acceptance criteria — what is being built, and how far it got. How to work through it is written in that file, not here.
  • Every file states its own terms. Its frontmatter says how binding it is, who may write to it, whether it is still active, and — in the description — what does not belong in it. Read that before editing; it beats guessing from the filename.
  • The body of a file is yours; its frontmatter is not. Every heading, table and section you find in these files is a starting suggestion — reshape any of it to fit the project, and delete what does not apply rather than leaving it empty. The six frontmatter fields are the exception: they are what make a file part of kiacontext, so keep all six on every file and keep their values current.
  • Writing back is part of the work, not an afterthought. A session that changes the project and leaves these files untouched has thrown away everything it learned.

Read the full file on GitHub · 111 lines

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.

  1. 1mo ago First seen · 111 lines · 1,716 tokens per session scan A befdc0926196

Subscribe to this mod's changes

open-scholar-peer CLAUDE.md is an instructions file published in the GitHub repository amirkiarafiei/open-scholar-peer (51 stars, last pushed 5d ago), licensed MIT. It adds 1,716 tokens to every session, about $0.0069 per session on Opus 5.5. 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 2026-09-12.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens