agentmods.dev

review-agent

A set of rules for examining an AI agent’s design against a collection of best-practice documents. The review checks how the agent is orchestrated, prompted, secured, tested, and operated.

In plain words
What is it for?
Use it to audit an agent built with frameworks such as LangChain, LangGraph, AutoGen, CrewAI, the OpenAI Agents SDK, or a custom system.
Why use it?
It reveals gaps and risks in an agent design before changes are made.

Cursor rule for Cursor

3 3mo ago A scan 33 tokens original MIT
View the source file sarkarsaurabh27/agent-loop-learning
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 rules/sarkarsaurabh27/agent-loop-learning/review-agent
Clone the repo
git clone --depth 1 https://github.com/sarkarsaurabh27/agent-loop-learning

Made for: Cursor.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00033 $0.00552
Opus 5 $0.00016 $0.00276
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 2d ago against content hash 3d0ee17a9663, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-agent 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.

.cursor/rules/review-agent.mdc · 58 lines

What it actually says

Review Agent Design

When the user asks to review, audit, or check an agent design:

  1. Explore the current repo first — do not ask the user for anything yet. Search for agent-related code:

    • Files matching *agent*, *tool*, *prompt*, *chain*, *workflow* in src/, lib/, app/, root
    • Imports of agent frameworks: langchain, langgraph, openai, anthropic, autogen, crewai
    • System prompt definitions, tool definitions, agent loop logic
    • CLAUDE.md, AGENTS.md, or any README describing the agent architecture Read the relevant files. Only ask the user if no agent code is found after exploring.

  2. Read all 9 best-practice docs from best-practices/:

    • 01-multi-agent-orchestration.md
    • 02-worker-prompting.md
    • 03-context-and-memory.md
    • 04-tool-design.md
    • 05-verification-and-testing.md
    • 06-security-and-permissions.md
    • 07-prompt-engineering.md
    • 08-performance-and-startup.md
    • 09-benchmarks-reference.md

  3. Score each dimension: ✅ Solid / ⚠️ Partial / ❌ Gap

  4. Output format:

### Agent Review: [name]

**Summary** (2–3 sentences)

| # | Dimension | Score | Finding |
|---|-----------|-------|---------|
| 01 | Orchestration | ✅/⚠️/❌ | ... |
| 02 | Worker prompting | | |
| 03 | Context & memory | | |
| 04 | Tool design | | |
| 05 | Verification | | |
| 06 | Security | | |
| 07 | Prompt engineering | | |
| 08 | Performance | | |

#### Top 3 improvements
For each: What / Why (cite benchmark) / How (implementation sketch)

#### What's already strong
2–3 callouts
  1. Always cite benchmark numbers with source — e.g. "17.2× → 4.4× error amplification (Google DeepMind, Dec 2025)".
  2. Framework-agnostic analysis. Note if any finding is model-specific.
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 · 58 lines · 33 tokens per session scan A 3d0ee17a9663

Subscribe to this mod's changes

review-agent is a cursor rule published in the GitHub repository sarkarsaurabh27/agent-loop-learning (3 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 552 once invoked, about $0.0002 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.

Code reviewWriting and docs
Related

Other cursor rules, from other repositories

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens

cli-error-handling

CLI command error handling patterns.

prisma/orm · 0 tokens

prefer-direct-imports-over-module-mocks

Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.

prisma/orm · 0 tokens

control-plane-descriptors

Control plane descriptor and instance implementation patterns.

prisma/orm · 0 tokens

family-instance-domain-actions

Family instance domain action implementation patterns.

prisma/orm · 0 tokens