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.
/plugin marketplace add devswha/oh-my-gajae-code/plugin install oh-my-gajae-codeWrote 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/skills/devswha/oh-my-gajae-code/insane-review)<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>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 5.1 | $0.00173 | $0.04404 |
| Opus 5 | $0.00086 | $0.02202 |
| Sonnet 5 | $0.00035 | $0.00881 |
| Haiku 4.5 | $0.00017 | $0.00440 |
Grade A, and why
insane-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
insane-review (gjc 포트)
왜 존재하나: GPT-5.6 Sol Pro는 웹(구독)에서만 쓸 수 있고 API가 없다. 그래서 Codex CLI·API provider·agent-council의 기존 API 멤버로는 못 부른다. 이 스킬은 구독 ChatGPT 웹을 CDP로 자동화해 Pro를 gjc 안으로 끌어오는 유일한 경로다. API 비용 0, 사용자의 요금제로 동작.
핵심 가치는 "통째 패킹"이 아니라 "의도 파악 → 관련 타겟만 정밀 선별 → 그것만 패킹" 이다. 이 선별을 gjc(너)가 수행하는 것이 이 도구의 차별점이다.
엔진은 hardened local engine이다. 실제 패킹·CDP 구동·모델검증·턴판정·회수는 감사된 로컬 DOM·보안 패치를 포함한
bin/pack_and_ask.py(Playwright 기반)가 수행한다. 로직을 gjc의browser도구로 재구현하지 마라 — 이 엔진의 검증 경계를 유지한다.
엔진 경로 해석 ($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.
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.
- 8d ago First seen · 163 lines · 173 tokens per session scan A ca55a3e46579
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…