task-review

A required checklist for completing a task, including checking requirements, reviewing rules, fixing issues, and validating the result before marking it complete.

In plain words
What is it for?
Use it at the end of a coding task to compare the implementation with its product and technical requirements and complete the required validation steps.
Why use it?
It reduces the chance of declaring work finished before it matches the requirements and passes final checks.

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/compozy/gograph/task-review
Clone the repo
git clone --depth 1 https://github.com/compozy/gograph

Made for: Cursor.

Per session 1,418 This file is loaded in full into every session.
When invoked 1,418 The same file — it is already loaded in full.
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 $0.01418 $0.01418
Opus 5 $0.00709 $0.00709
Sonnet 5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured 2d ago against content hash 1fc3e2c3ca5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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 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/task-review.mdc · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Completion Workflow with Zen MCP

<critical_requirement> MANDATORY: Before marking any task as complete, you MUST follow this exact workflow to ensure code quality: </critical_requirement>

<workflow_overview> Enhanced Quality Assurance Steps:

  1. Task Definition Validation - Verify alignment with task, PRD, and tech spec
  2. Rules Analysis & Code Review - Analyze applicable rules and perform comprehensive review
  3. Issue Resolution - Address all identified problems
  4. Pre-Commit Validation - Final validation before commit
  5. Task Completion - Mark task as complete only after successful validation </workflow_overview>

1. Task Definition Validation

<mandatory_step> FIRST: Verify the implementation aligns with requirements: </mandatory_step>

  • Task Definition: Review the specific task file (e.g., tasks/prd-[feature-slug]/[task_number]_task.md)
  • PRD Alignment: Check against the Product Requirements Document (tasks/prd-[feature-slug]/_prd.md)
  • Tech Spec Compliance: Ensure implementation follows the Technical Specification (tasks/prd-[feature-slug]/_techspec.md)
Verify that task [task_number] implementation fully satisfies:
1. The specific requirements defined in the task file
2. The business objectives from the PRD
3. The technical specifications and architecture requirements
4. All acceptance criteria and success metrics

2. Rules Analysis & Code Review with Zen MCP

<mandatory_step> Analyze applicable rules first, then perform comprehensive code review: </mandatory_step>

2.1 Rules Analysis

Analyze all Cursor rules that apply to the changed files for task [task_number]:
- Identify which .cursor/rules/*.mdc files are relevant to the implementation
- List the specific coding standards, patterns, and requirements that apply
- Check for any rule violations or areas needing attention

2.2 Multi-Model Code Review

<mandatory_step> Use the criteria from review-checklist.mdc as the basis for all code reviews: </mandatory_step>

Read the full file on GitHub · 155 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 · 155 lines · 1,418 tokens per session scan A 1fc3e2c3ca5a

Subscribe to this mod's changes

task-review is a cursor rule published in the GitHub repository compozy/gograph (9 stars, last pushed 1y ago), licensed MIT. It adds 1,418 tokens to every session, about $0.0071 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.