code-review-standards

A set of rules for deciding whether automated code-review feedback is correct in the full context of a project.

In plain words
What is it for?
It guides explanations for accepting or declining review comments about repeated values, concurrency risks, and other static-analysis findings.
Why use it?
It helps developers address valid review findings without changing code for suggestions that do not apply, such as unnecessary constants or theoretical race conditions.

Cursor rule for Cursor

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/technickai/ai-coding-config/code-review-standards
Clone the repo
git clone --depth 1 https://github.com/TechNickAI/ai-coding-config

Made for: Cursor.

Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 547 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 $0.00004 $0.00547
Opus 5 $0.00002 $0.00273
Sonnet 5 $0.00001 $0.00109
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash 7e18fe3bbe2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-standards 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/code-review-standards.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Standards

This rule defines when bot feedback is incorrect given context bots lack. Use this to identify suggestions that don't apply, not to skip valid feedback based on priority.

Core Philosophy

Address all suggestions where the bot's analysis is correct given full context. Decline when you can articulate why the bot's reasoning doesn't hold - valid declines explain why the analysis is incorrect, not why addressing it is inconvenient.

When Bot Suggestions Don't Apply

These patterns describe situations where bot analysis is typically incorrect. Decline with explanation when you can demonstrate the bot's reasoning doesn't hold.

Single-Use Values

Bots flag inline values as "magic strings" needing extraction. This suggestion is wrong when the value appears exactly once and context makes the meaning clear. Extracting METHOD_INITIALIZE = "initialize" for a single use adds indirection without DRY benefit. Constants exist to stay DRY across multiple uses, not to avoid inline values.

Theoretical Race Conditions

Bots flag potential race conditions based on static analysis. This suggestion is wrong when operations are already serialized by a queue, mutex, or transaction the bot can't see. Add synchronization when profiling or testing reveals actual race conditions.

Redundant Type Safety

Bots suggest stricter types or null checks. This suggestion is wrong when runtime validation already handles the case correctly, or when the type system guarantees the condition can't occur. TypeScript serves the code - working code with runtime safety takes priority over compile-time type perfection.

Premature Optimization

Bots flag performance concerns without data. This suggestion is wrong when no profiling shows actual performance problems. Optimize based on measurements - complexity should yield measurable performance gains.

Items Requiring Case-by-Case Judgment

These require evaluation in context - sometimes the bot is right, sometimes wrong.

Read the full file on GitHub · 70 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 · 70 lines · 4 tokens per session scan A 7e18fe3bbe2e

Subscribe to this mod's changes

code-review-standards is a cursor rule published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 2mo ago), licensed MIT. It adds 4 tokens to every session and 547 once invoked, about $0.0000 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 2026-08-30.