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.
npx agentmods add instructions/rijul1204/rashedul-agentic-engineering/code-reviewgit clone --depth 1 https://github.com/Rijul1204/rashedul-agentic-engineeringWhat 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 | $0.00707 | $0.00707 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
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.
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.ymlreads 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. Preferunknown+ narrowing. Usesatisfiesfor 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.allor React'scache()."
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:
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.
- 2d ago First seen · 81 lines · 707 tokens per session scan A a770531b7c3a
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.
Other instructions, from other repositories
onedev AGENTS.md
AGENTS.md instructions for theonedev/onedev: Do not add Co-authored-by: or other co-author / AI attribution footers to commit messages unless the user explicitly asks for them. If such a trailer is injected into a commit you just created (and it is not pushed), rewrite the commit message to remove it before finishing.
veritas-kanban AGENTS.md
Instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
operator CLAUDE.md
Instructions for untra/operator, covering claude.md - operator, project overview, tech stack, code style and plans & specs location.
jjj AGENTS.md
Instructions for doug/jjj, covering agent instructions, before you write anything, read this first, house rules and verifying changes to this repository.
oh-my-symphony AGENTS.md
Instructions for cskwork/oh-my-symphony, covering agents.md: codex cli entry point, source of truth: skills/symphony-skill, available skill (operator-facing), symphony-skill and worker-side guidance.