insane-review

insane-review is a skill for Claude Code from devswha/oh-my-gajae-code. It costs 173 tokens per session (4,404 once invoked), scanned A, original, MIT.

A code-review skill that sends carefully selected repository code to a subscribed ChatGPT Pro web session for a second opinion. It uses a local browser-automation process to collect the relevant files and retrieve the review.

In plain words
What is it for?
Use it for code reviews, debugging opinions, design feedback, or requests to ask ChatGPT Pro about a specific implementation.
Why use it?
It helps obtain another model’s view when reviewing code or investigating a problem, without sending the entire repository by default. Selecting only relevant files keeps the review focused.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: positional $N argument; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the oh-my-gajae-code plugin — 5 skills shipped together

Good fit Use it for code reviews, debugging opinions, design feedback, or requests to ask ChatGPT Pro about a specific implementation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add devswha/oh-my-gajae-code
Claude Code
/plugin install oh-my-gajae-code

Made for: Claude Code.

Or install oh-my-gajae-code, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

agentmods badge for insane-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/devswha/oh-my-gajae-code/insane-review.svg)](https://agentmods.dev/skills/devswha/oh-my-gajae-code/insane-review)
Your own site
<a href="https://agentmods.dev/skills/devswha/oh-my-gajae-code/insane-review"><img src="https://agentmods.dev/badge/skills/devswha/oh-my-gajae-code/insane-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00173 $0.04404
Opus 5 $0.00086 $0.02202
Sonnet 5 $0.00035 $0.00881
Haiku 4.5 $0.00017 $0.00440

Measured 8d ago against content hash ca55a3e46579, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

insane-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 8d 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.

plugins/oh-my-gajae-code/skills/insane-review/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

insane-review (gjc 포트)

왜 존재하나: GPT-5.6 Sol Pro는 웹(구독)에서만 쓸 수 있고 API가 없다. 그래서 Codex CLI·API provider·agent-council의 기존 API 멤버로는 못 부른다. 이 스킬은 구독 ChatGPT 웹을 CDP로 자동화해 Pro를 gjc 안으로 끌어오는 유일한 경로다. API 비용 0, 사용자의 요금제로 동작.

핵심 가치는 "통째 패킹"이 아니라 "의도 파악 → 관련 타겟만 정밀 선별 → 그것만 패킹" 이다. 이 선별을 gjc(너)가 수행하는 것이 이 도구의 차별점이다.

엔진은 hardened local engine이다. 실제 패킹·CDP 구동·모델검증·턴판정·회수는 감사된 로컬 DOM·보안 패치를 포함한 bin/pack_and_ask.py(Playwright 기반)가 수행한다. 로직을 gjc의 browser 도구로 재구현하지 마라 — 이 엔진의 검증 경계를 유지한다.

엔진 경로 해석 ($IR) — 매 실행 전 1회

${CLAUDE_PLUGIN_ROOT} 같은 치환은 gjc 커맨드/스킬 본문에서 동작하지 않는다. 네이티브 설치가 scope마다 기록한 정확한 suite root binding(root, mode 0600)만 사용한다. 새 프로젝트 binding($PWD/.gjc/runtimes/oh-my-gajae-code/root)과 새 user binding($HOME/.gjc/agent/runtimes/oh-my-gajae-code/root)을 순서대로 읽는다. 둘 다 없을 때만 읽기 전용·기간 한정 compatibility fallback인 기존 oh-my-gjc 프로젝트/user binding을 같은 순서로 읽고, 그마저 없을 때만 이 checkout의 정확한 plugins/oh-my-gajae-code/ asset으로 fallback한다. 기존 binding이나 user state는 쓰거나 지우지 않는다:

resolve_omg_asset() (
  fail() { echo "oh-my-gajae-code runtime binding is missing or invalid; rerun https://raw.githubusercontent.com/devswha/oh-my-gajae-code/main/install.sh." >&2; exit 1; }
  reject_symlinked_components() {
    local path="$1" current="/" component
    local -a components
    case "$path" in /*) ;; *) fail ;; esac
    IFS=/ read -r -a components <<<"${path#/}"
    for component in "${components[@]}"; do
      [ -n "$component" ] || continue
      current="${current%/}/$component"
      [ ! -L "$current" ] || fail
    done
  }
  local expected_asset="$1" binding root bytes byte asset asset_dir canonical_root canonical_asset_dir checkout
  local -a bindings=(
    "$PWD/.gjc/runtimes/oh-my-gajae-code/root"
    "$HOME/.gjc/agent/runtimes/oh-my-gajae-code/root"
  )
  # Bounded read-only compatibility fallback; never mutate legacy paths.
  local -a legacy_compatibility_bindings=(
    "$PWD/.gjc/runtimes/oh-my-gjc/root"
    "$HOME/.gjc/agent/runtimes/oh-my-gjc/root"
  )
  bindings+=("${legacy_compatibility_bindings[@]}")
  for binding in "${bindings[@]}"; do
    if [ -e "$binding" ] || [ -L "$binding" ]; then
      reject_symlinked_components "$binding"
      [ -f "$binding" ] && [ ! -L "$binding" ] || fail
      bytes="$(LC_ALL=C od -An -v -tu1 "$binding")" || fail
      for byte in $bytes; do
        case "$byte" in 0|[1-9]|1[1-9]|2[0-9]|3[01]|127) fail ;; esac
      done
      exec 3< "$binding" || fail
      IFS= read -r root <&3 || { exec 3<&-; fail; }
      if IFS= read -r -n 1 _ <&3; then exec 3<&-; fail; fi
      exec 3<&-
      case "$root" in ""|*[[:cntrl:]]*) fail ;; /*) ;; *) fail ;; esac
      canonical_root="$(cd -P -- "$root" 2>/dev/null && pwd -P)" || fail
      [ "$root" = "$canonical_root" ] || fail
      asset="$canonical_root/$expected_asset"
      asset_dir="${asset%/*}"
      canonical_asset_dir="$(cd -P -- "$asset_dir" 2>/dev/null && pwd -P)" || fail
      [ "$asset_dir" = "$canonical_asset_dir" ] && [ -f "$asset" ] && [ ! -L "$asset" ] || fail
      printf '%s\n' "$asset"
      exit 0
    fi
  done
  checkout="$PWD/plugins/oh-my-gajae-code"
  reject_symlinked_components "$checkout"
  [ -d "$checkout" ] && [ ! -L "$checkout" ] || fail
  canonical_root="$(cd -P -- "$checkout" 2>/dev/null && pwd -P)" || fail
  asset="$canonical_root/$expected_asset"
  asset_dir="${asset%/*}"
  canonical_asset_dir="$(cd -P -- "$asset_dir" 2>/dev/null && pwd -P)" || fail
  [ "$asset_dir" = "$canonical_asset_dir" ] && [ -f "$asset" ] && [ ! -L "$asset" ] || fail
  printf '%s\n' "$asset"
)
IR="$(resolve_omg_asset "bin/pack_and_ask.py")" || exit 1
echo "IR=$IR"

Malformed, symlinked, non-canonical, multiline, control-character-containing, or asset-missing binding fails closed. Do not select a plugin cache; bootstrap, upgrade, or repair by rerunning the hardened root installer at https://raw.githubusercontent.com/devswha/oh-my-gajae-code/main/install.sh.

Read the full file on GitHub · 163 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. 8d ago First seen · 163 lines · 173 tokens per session scan A ca55a3e46579

Subscribe to this mod's changes

insane-review is a skill published in the GitHub repository devswha/oh-my-gajae-code (34 stars, last pushed 19d ago), licensed MIT. It adds 173 tokens to every session and 4,404 once invoked, about $0.0009 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.