decision-review

decision-review is a cursor rule for Cursor from Jkudjo/oh-my-cursor. It costs 11 tokens per session (707 once invoked), scanned A, original, MIT.

A reasoning audit for completed coding tasks. It examines how the problem was framed, how possible causes were considered, and how risks were judged—not only whether the code works.

In plain words
What is it for?
Use it after significant work to assess problem framing, hypotheses, scope, risk estimates, and lessons for future tasks.
Why use it?
It helps reveal when a task solved a symptom, used an untested assumption, or changed more than necessary. The review creates a record of weaknesses in the decision process.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it after significant work to assess problem framing, hypotheses, scope, risk estimates, and lessons for future tasks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/jkudjo/oh-my-cursor/decision-review
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.

Clone the repo
git clone --depth 1 https://github.com/Jkudjo/oh-my-cursor

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for decision-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/decision-review.svg)](https://agentmods.dev/rules/jkudjo/oh-my-cursor/decision-review)
Your own site
<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/decision-review"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/decision-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00011 $0.00707
Opus 5 $0.00005 $0.00353
Sonnet 5 $0.00002 $0.00141
Haiku 4.5 $0.00001 $0.00071

Measured 7d ago against content hash cd5b27b68f7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

decision-review 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 7d 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.

rules/decision-review.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@decision-review

Trigger: After completing a significant task. Reviews the quality of the reasoning process, not just the output.

This is the meta-layer above @review (which reviews code). @decision-review reviews the decisions that led to the code.

Protocol

Load the session artifacts: diagnosis, plan, implementation approach, and review results.

Evaluate each dimension:

1. Problem framing

  • Was the problem correctly identified, or was a symptom treated as the root cause?
  • Was scope appropriately bounded — not too narrow (missing real cause) or too wide (unnecessary changes)?
  • Score 1–5: 1=solved wrong problem, 5=correctly identified and bounded the real problem

2. Hypothesis quality

  • Were alternative causes considered before committing to the leading theory?
  • Was the hypothesis tree broad enough to catch non-obvious causes?
  • Was any hypothesis held too long against contradicting evidence?
  • Score 1–5: 1=first theory, never reconsidered, 5=full tree, updated on contradictions

3. Risk estimation

  • Were risks accurately estimated, or understated?
  • Was blast radius correctly scoped?
  • Were there surprises during execution that should have been anticipated?
  • Score 1–5: 1=ignored risks, 5=accurately predicted all relevant risks

4. Decision under uncertainty

  • When information was missing, were assumptions made explicit?
  • Were decisions appropriately deferred when uncertainty was high?
  • Was overconfidence present anywhere?
  • Score 1–5: 1=confident with no evidence, 5=uncertainty always labelled, deferral where appropriate

5. Verification quality

  • Was a clear success criterion defined before starting?
  • Was the fix verified against the actual root cause, not just surface symptoms?
  • Score 1–5: 1=no verification, 5=exact metric proved the fix worked

Output

## Decision Review: {task}

### Problem framing:       X/5
### Hypothesis quality:    X/5
### Risk estimation:       X/5
### Decision under uncertainty: X/5
### Verification quality:  X/5

**Total: XX/25**

### What was done well
[specific]

### What should be different next time
[specific, actionable]

### Pattern to encode
[if a systematic weakness is found — what rule would prevent it?]

Read the full file on GitHub · 84 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. 7d ago First seen · 84 lines · 11 tokens per session scan A cd5b27b68f7f

Subscribe to this mod's changes

decision-review is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 707 once invoked, about $0.0001 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.

Related

Other cursor rules, from other repositories