Vf Review — Security skill for Claude Code
Parallel Salesforce code review of the diff against a base ref - dispatch the quality gate and security reviewer in one batch, merge and deduplicate findings, and report them by severity with an over.
How to install Vf Review
Installs to ~/.claude/skills/grzmol-vibe-force-vf-review/SKILL.md
mkdir -p ~/.claude/skills/grzmol-vibe-force-vf-review && curl -fsSL https://raw.githubusercontent.com/grzmol/vibe-force/HEAD/commands/vf-review.md -o ~/.claude/skills/grzmol-vibe-force-vf-review/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Vf Review does
description: Parallel Salesforce code review of the diff against a base ref - dispatch the quality gate and security reviewer in one batch, merge and deduplicate findings, and report them by severity with an over-build dimension. argument-hint: "[base-ref]" allowed-tools: Task, Read, Grep, Glob, Bash(git diff:*), Bash(git merge-base:*), Bash(git rev-parse:*), Bash(git log:*)
vf-review - parallel review of a diff
Raw arguments: `$ARGUMENTS`
`BASE` = the first argument, or `origin/mai
Alternatives in Security
- /chain — Build an A→B→C exploit chain for higher severity and payout 927 ★
- Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★
- Engage.Cvediff — Find the canonical fix commit(s) for a CVE across sources, then diff for root cause 348 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Gaia Debt
Fix the tech-debt backlog, a single issue or a recommended related batch, highest severity then oldest first,
Ship Check
End-of-session production audit with auto-merge. Reconstructs session intent, then RUNS the full review chain
Salesforce Core Skills
Fifteen behaviorally-tested Salesforce skills for AI agents — Apex, Flow, SOQL, LWC, Metadata, Permissions, Di
Dotnet Review
Multi-agent .NET code review - up to five reviewers in parallel (correctness, performance, security/observabil
Audit Plan
Dispatch the plan-reviewer sub-agent to audit the active feature's spec.md and plan.md against PLANNING.md and
Horde Test Skill
Execute comprehensive testing plans using horde-swarm to dispatch parallel test agents across multiple test ca
Related Agents
Research Processor
Post-process research results — condense findings or deduplicate parallel agent outputs. Two modes.
Code Review Cold
Spec-blind adversarial code reviewer for canon code_review. Reviews only the diff and base ref, then returns s
Branch Reviewer
Reviews a whole branch before merge and proposes knowledge-base improvements from the batch's audits and revie