rashedul-agentic-engineering code-review.instructions.md

A starter set of instructions for automated code reviews, where a tool examines proposed changes against a project-specific checklist. It covers areas such as architecture, framework conventions, and type safety.

In plain words
What is it for?
Use it to define review guidance for a repository, including its framework, architecture, coding conventions, type rules, and important pitfalls.
Why use it?
It gives automated reviews consistent rules and limits them to the changed code instead of relying on vague review requests.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/rijul1204/rashedul-agentic-engineering/code-review
Clone the repo
git clone --depth 1 https://github.com/Rijul1204/rashedul-agentic-engineering

Made for: GitHub Copilot.

Per session 707 This file is loaded in full into every session.
When invoked 707 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00707 $0.00707
Opus 5 $0.00353 $0.00353
Sonnet 5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 2d ago against content hash a770531b7c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rashedul-agentic-engineering code-review.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 2d 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.

workflows/claude-code-review/.github/instructions/code-review.instructions.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automated Code Review Guidelines

Replace this file with your repo's review rubric before relying on the workflow.

This is a starter template. The workflow at .github/workflows/cursor_review.yml reads this file (and any {{MODULE:...}} files under .github/instructions/modules/) verbatim into the review prompt, so anything written here becomes the rubric Cursor uses on every PR.

Context: Briefly describe what this repo is — framework, language, architecture, key conventions. The reviewing agent uses this to calibrate its expectations. Example: "This is a Next.js 15 monorepo using TypeScript, Drizzle ORM, and Tailwind. Apps live under apps/, shared code under packages/."

CRITICAL: Review ONLY the code changes shown in the diff below. Do NOT review files that weren't changed.


What to check

List the conventions, patterns, and pitfalls that matter for this repo. Group by theme. Suggested sections:

Framework & architecture

  • Bullet specific patterns the framework enforces or that your team has agreed on.
  • E.g. "Server Components by default; only mark 'use client' when the component uses hooks or browser APIs."

Type safety

  • E.g. "No any. Prefer unknown + narrowing. Use satisfies for inferred-but-checked literals."

Data layer

  • E.g. "All DB writes go through the repository layer (lib/db/repos/), never inline Drizzle calls in route handlers."

Security

  • Flag unsanitized HTML injection paths (e.g. raw HTML inserted into the DOM without an explicit sanitizer).
  • No secrets, tokens, or API keys committed.
  • Inputs crossing trust boundaries must be validated before use.

Performance

  • E.g. "Avoid waterfall fetches in Server Components — use Promise.all or React's cache()."

Testing

  • E.g. "Every new public function gets a vitest unit test; every new route gets an integration test."

Optional: modular rules

For larger rubrics, split rules into files under .github/instructions/modules/ and reference them here:

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 707 tokens per session scan A a770531b7c3a

Subscribe to this mod's changes

rashedul-agentic-engineering code-review.instructions.md is an instructions file published in the GitHub repository Rijul1204/rashedul-agentic-engineering (2 stars, last pushed 1mo ago), licensed MIT. It adds 707 tokens to every session, about $0.0035 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.