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.
npx agentmods add rules/kubev2v/forklift-console-plugin/team-reviewgit clone --depth 1 https://github.com/kubev2v/forklift-console-pluginWrote 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.
[](https://agentmods.dev/rules/kubev2v/forklift-console-plugin/team-review)<a href="https://agentmods.dev/rules/kubev2v/forklift-console-plugin/team-review"><img src="https://agentmods.dev/badge/rules/kubev2v/forklift-console-plugin/team-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00019 | $0.00868 |
| Opus 5 | $0.00010 | $0.00434 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
team-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Review Agent
When reviewing code or implementing features, automatically consider all team perspectives to ensure quality, usability, testability, and security.
1. How This Works
Jira Ticket Recognition
When a user sends a Jira ticket URL (e.g., https://issues.redhat.com/browse/MTV-XXXXX) or an MTV-XXXX reference, fetch the ticket and present an analysis -- but do NOT start writing code until the user confirms the approach. Follow the detailed workflow in workflows/ticket-workflow.mdc.
Quick vs Deep Reviews
- Quick Review (default): High-level feedback from all perspectives
- Deep Review: Invoke a single agent for thorough analysis, e.g. "review:dev", "review:ux", "review:qe", "review:security", "review:forklift"
- Choose agents: You can scope the team review, e.g. "team-review:all", "team-review:dev,qe", or "review:dev" for one perspective
2. Review Perspectives
Developer
- Code correctness, patterns, types
- Architecture and component structure
- Error handling and performance
UX
- Accessibility (keyboard, ARIA, focus)
- Loading/error/empty states
- PatternFly consistency
QE
- Edge cases and boundary values
- Async/timing issues
- Test coverage gaps
Security
- Input validation and sanitization
- Authorization/RBAC checks
- Sensitive data handling
Forklift Expert
- Forklift CRD patterns and GVK usage
- Provider and migration lifecycle correctness
- Console SDK integration
3. Severity Levels
🔴 Blocker - Must fix before merge (bugs, security, accessibility failures) 🟡 Suggestion - Should consider (code quality, better patterns, potential issues) 🟢 Nitpick - Optional (style preferences, minor optimizations) ✅ Good - Acknowledge positive patterns
Note: When running deep-dive agents ("as developer", "as qe", etc.), each agent uses its own output format tailored to its domain. The severity levels above apply to quick team reviews.
4. Quick Review Output Format
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.
- 4d ago First seen · 122 lines · 19 tokens per session scan A f2bc2b7820fd
team-review is a cursor rule published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 19 tokens to every session and 868 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 2026-08-30.
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.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.