reexamine_process

A fresh-eyes quality check performed after substantial coding work. It reviews the result for accessibility, error handling, visual details, keyboard use, performance, and related areas.

In plain words
What is it for?
Use it after features, fixes, refactors, or UI work—and before marking the task complete—to inspect adjacent code, fix issues, and review the fixes again.
Why use it?
It catches problems that are easy to miss when checking only whether the code works.

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/homenshum/nodebenchai/reexamine_process
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 402 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 $0.00000 $0.00402
Opus 5 $0.00000 $0.00201
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash f8b6485769ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reexamine_process 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/reexamine_process.mdc · 33 lines

What it actually says

Re-examine for 11/10

After completing any non-trivial change, do a fresh-eyes pass to elevate from "correct" to "exceptional."

When to trigger

  • After any feature, fix, or refactor touching 3+ files or 50+ lines
  • After any UI/dashboard/component work
  • Before marking a task as "done"

The process

  1. Step back: Stop coding. Read the output as a first-time user would.
  2. Scan each related_ domain: Walk the related_ list below — each is a focused checklist.
  3. Fix what you find: Don't just note issues — fix them in the same pass.
  4. Re-examine the fixes: New code can introduce new gaps. One more scan.
  • Accessibility gaps? → reexamine_a11y
  • Error resilience? → reexamine_resilience
  • Visual polish / micro-interactions? → reexamine_polish
  • Keyboard efficiency? → reexamine_keyboard
  • Performance / progressive disclosure? → reexamine_performance

Anti-patterns

  • Skipping the re-examine because "it works"
  • Re-examining only your own changes (check adjacent code too)
  • Adding complexity without user benefit (re-examine is about polish, not gold-plating)
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 · 33 lines · 402 tokens per session scan A f8b6485769ec

Subscribe to this mod's changes

reexamine_process is a cursor rule published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 402 tokens. 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.