From kizunax
Adversarial code review (skeptic stance, attack surface, failure modes)
How this command is triggered — by the user, by Claude, or both
Slash command
/kizunax:adversarial-review [target-flags] [--paths a,b/] [--focus TEXT] [--verbose]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Run a Kizunax adversarial review (security-minded, skeptic stance, attack surface focus).
Steps:
1. Verify `${CLAUDE_PLUGIN_ROOT}/bin/kizunax` exists. If not, instruct the user to run `/kizunax:setup` first.
2. Run:
3. Return the command stdout verbatim. Do not paraphrase, summarize, or add commentary.
4. Do not fix any issues mentioned in the review output. The plugin is read-only.
Same target flags as `/kizunax:review`. Adversarial mode focuses on:
- Attack surface (injection, auth bypass, traversal)
- Concurrency & race conditions
- Failure modes (nil/empty/malformed/very-large...Run a Kizunax adversarial review (security-minded, skeptic stance, attack surface focus).
Steps:
Verify ${CLAUDE_PLUGIN_ROOT}/bin/kizunax exists. If not, instruct the user to run /kizunax:setup first.
Run:
${CLAUDE_PLUGIN_ROOT}/bin/kizunax adversarial-review $ARGUMENTS
Return the command stdout verbatim. Do not paraphrase, summarize, or add commentary.
Do not fix any issues mentioned in the review output. The plugin is read-only.
Same target flags as /kizunax:review. Adversarial mode focuses on:
Use --focus "auth flow" (or similar) to direct attention to a specific concern.
npx claudepluginhub thanhhaudev/kizunax-plugin-cc --plugin kizunax/adversarial-reviewRuns adversarial Codex review challenging implementation approach, design choices, tradeoffs, and assumptions on git-scoped codebase. Supports --wait, --background, --base <ref>, --scope, focus args.
/adversarial-reviewRun a Gemini review that challenges the implementation approach and design choices
/adversarial-reviewRun a Copilot review that challenges the implementation approach and design choices
/adversarial-reviewRuns an adversarial Pi review that challenges implementation approach, design choices, tradeoffs, and assumptions. Returns raw review output from the companion script.
/adversarial-reviewRun a Qwen review that challenges the implementation approach and design choices