Borrowing it
Nothing to install: this file belongs to zfy465914233/scholar-agent. 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/zfy465914233/scholar-agent/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/zfy465914233/scholar-agentWrote 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/zfy465914233/scholar-agent/copilot-instructions)<a href="https://agentmods.dev/instructions/zfy465914233/scholar-agent/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zfy465914233/scholar-agent/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00528 | $0.00528 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
scholar-agent copilot-instructions.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 8d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Instructions
Project Context
This is Scholar Agent — a knowledge flywheel MCP server with an academic paper research pipeline. It combines domain knowledge retrieval, structured research synthesis, and academic paper analysis (arXiv/Semantic Scholar/DBLP).
Core Constraints
- Backend academic search runs via public APIs (OpenAlex, Semantic Scholar, DBLP) — zero API keys needed for the backend layer. General web search is delegated to the LLM's built-in search capability. Frontend reasoning uses online models (Claude, Copilot) which require their own API access.
- No local LLM is needed.
- Evidence-first. Never present conclusions without citing sources.
- All outputs must include temporal context — when was the evidence retrieved, when was it published.
- For "best option" questions, always state the evaluation criteria (freshness, engineering maturity, community activity, reproducibility).
Output Principles
- Prefer structured output over prose.
- Explicitly mark uncertainty — distinguish "confirmed" from "likely" from "unknown".
- Avoid marketing-style summaries. Prefer reproducibility and engineering maturity over hype.
- When comparing options, use tables with consistent dimensions.
Evidence Handling
- All evidence must conform to the project evidence schema (
src/scholar_agent/schemas/evidence.schema.json). - Conclusions must explicitly link back to evidence items.
- When evidence conflicts, surface the conflict rather than silently picking a side.
Knowledge Organization
- Organize
knowledge/primarily by narrow topic folders such asqpe/,markov_chain/,quantum_phase_estimation/,linear_programming/, andmodel_quantization/. - Do not create deeper type-based folders like
definitions/,methods/, ortheorems/under a domain. Keep files directly inside the domain folder. - Use frontmatter metadata such as
typeto distinguish definitions, methods, theorems, derivations, comparisons, and decision records. - When draft-stage or promotion-stage files need to coexist with curated materials, distinguish them with filename prefixes such as
draft-andcandidate-. - Each topic folder should include a short
README.mddescribing what belongs there and how filenames are used. - Shared templates live in
src/scholar_agent/templates/(paper analysis). Knowledge cards should not have nested template folders.
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.
- 8d ago First seen · 40 lines · 528 tokens per session scan A 93f8daf2d317
scholar-agent copilot-instructions.md is an instructions file published in the GitHub repository zfy465914233/scholar-agent (9 stars, last pushed yesterday), licensed MIT. It adds 528 tokens to every session, about $0.0026 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 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).
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.
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.