Skip to content

DevNullLtd/Yuzu / .claude/skills/adversarial-review

adversarial-review

Verified

Run an adversarial two-phase code review of a change with TWO independent reviewers — Claude and Codex — who review alone, then cross-examine each other's findings, then Claude synthesizes a single weighted verdict. Use when the user says "/adversarial-review", "adversarial review", "review this with Codex", "get Codex to review", "two-reviewer review", "cross-examine this PR", or wants a second independent model to grade a change before merge.

FileKindSize
SKILL.mdskill md11.9 KB
review-prompt.mdmarkdown7.6 KB
run-codex-reviewer.shexecutablescript5.0 KB
run-kimi-reviewer.shexecutablescript14.2 KB
run-kimi-sandbox-hook.shexecutablescript1.0 KB
run-kimi-sandboxed-shell.shexecutablescript1.9 KB

run-kimi-sandbox-hook.sh

View on GitHub
#!/usr/bin/env bash
# Intercept Kimi's one permitted empirical request. The native Bash deny rule
# remains in force after this hook, so hook failure cannot grant shell access.

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
EXPECTED="$SCRIPT_DIR/run-kimi-sandboxed-shell.sh"
INPUT="$(head -c 65536)"
COMMAND="$(python3 -c 'import json,sys; print(json.load(sys.stdin).get("tool_input", {}).get("command", ""))' <<<"$INPUT")"

if [[ "$COMMAND" != "$EXPECTED" ]]; then
  exit 0
fi

if "$EXPECTED"; then
  OUTPUT_FILE="${YUZU_KIMI_SANDBOX_REVIEW_DIR:?}/KIMI_SANDBOX_OUTPUT.md"
  OUTPUT="$(head -c 32768 "$OUTPUT_FILE" 2>/dev/null || true)"
  python3 -c 'import json,sys; print(json.dumps({"hookSpecificOutput":{"permissionDecision":"deny","permissionDecisionReason":"Sandbox collector completed; direct Bash remains denied. Collector output:\n" + sys.stdin.read()}}))' <<<"$OUTPUT"
else
  printf '%s\n' '{"hookSpecificOutput":{"permissionDecision":"deny","permissionDecisionReason":"Sandbox collector failed; direct Bash remains denied."}}'
fi
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall