update-ralph-x

update-ralph-x is a skill for Claude Code from kangraemin/ralph-x. It costs 15 tokens per session (1,304 once invoked), scanned C, original, MIT.

A skill that keeps replies in the language used by the user and guides updates for ralph-x, a tool or plugin that can check its own installed version. It also describes downloading and running an update-check script.

In plain words
What is it for?
Use it when responding to Korean- or English-speaking users about ralph-x installation, version checks, and approved updates.
Why use it?
It avoids language switching and gives a fixed process for checking whether ralph-x needs an update. The input does not describe other capabilities.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ralph-x plugin — 2 skills shipped together

Good fit Use it when responding to Korean- or English-speaking users about ralph-x installation, version checks, and approved updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kangraemin/ralph-x/update-ralph-x
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kangraemin/ralph-x --skill update-ralph-x
Clone the repo
git clone --depth 1 https://github.com/kangraemin/ralph-x

Made for: Claude Code.

Or install ralph-x, the plugin that ships this one along with the rest of its 2 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 update-ralph-x

README.md
[![agentmods](https://agentmods.dev/badge/skills/kangraemin/ralph-x/update-ralph-x/github.svg)](https://agentmods.dev/skills/kangraemin/ralph-x/update-ralph-x)
Your own site
<a href="https://agentmods.dev/skills/kangraemin/ralph-x/update-ralph-x"><img src="https://agentmods.dev/badge/skills/kangraemin/ralph-x/update-ralph-x/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update-ralph-x

Your own site · 80×15
<a href="https://agentmods.dev/skills/kangraemin/ralph-x/update-ralph-x"><img src="https://agentmods.dev/badge/skills/kangraemin/ralph-x/update-ralph-x.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00015 $0.01304
Opus 5 $0.00008 $0.00652
Sonnet 5 $0.00003 $0.00261
Haiku 4.5 $0.00002 $0.00130

Measured 10d ago against content hash 81eee4904d25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

update-ralph-x scanned grade C with 2 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `MOVED:N SKIPPED:M` → 결과 출력 후 "`.claude/ralph-x-runs/`를 삭제할까요?" 확인. 승인 시 `rm -rf .claude/ralph-x-runs`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf "https://raw.githubusercontent.com/kangraemin/ralph-x/main/scripts/update-check.sh" \
skills/update-ralph-x/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/update-ralph-x

Respond in the same language the user uses. Korean → Korean. English → English.

Step 1: 설치 경로 확인 + bootstrap

아래 코드를 그대로 실행한다. 경로나 파일명을 변경하지 않는다.

INSTALL_PATH=$(python3 -c "
import json
data = json.load(open('$HOME/.claude/plugins/installed_plugins.json'))
entries = data.get('plugins', {}).get('ralph-x@ralph-x', [])
print(entries[0]['installPath'] if entries else '')
")
SCRIPT="$INSTALL_PATH/scripts/update-check.sh"
if [ ! -f "$SCRIPT" ]; then
  mkdir -p "$INSTALL_PATH/scripts"
  curl -sf "https://raw.githubusercontent.com/kangraemin/ralph-x/main/scripts/update-check.sh" \
    -o "$SCRIPT" && chmod +x "$SCRIPT"
fi
echo "SCRIPT=$SCRIPT"
echo "EXISTS=$([ -f "$SCRIPT" ] && echo yes || echo no)"
  • EXISTS=no → "update-check.sh를 다운로드할 수 없습니다." 출력 후 종료
  • EXISTS=yes → Step 2 진행. $SCRIPT 값을 기억해둔다.

Step 2: 버전 확인

Step 1에서 얻은 $SCRIPT 경로를 그대로 사용:

bash "<Step 1에서 출력된 SCRIPT 경로>" --check-only

Step 3: 결과 처리

  • status: up-to-date → "최신 버전입니다 (SHA)" 출력 → Step 5로 이동
  • status: update-available → 현재/최신 SHA 보여주고 업데이트 여부 확인

Step 4: 업데이트 실행

사용자 승인 시:

bash "<Step 1에서 출력된 SCRIPT 경로>" --force

Step 4.5: .claude/ralph-x-runs/ 디렉토리 이동

아래 코드를 그대로 실행한다:

python3 -c "
import os, shutil, sys

old_dir = '.claude/ralph-x-runs'
new_dir = 'ralph-x-runs'

if not os.path.isdir(old_dir):
    print('NO_OLD_DIR')
    sys.exit(0)

os.makedirs(new_dir, exist_ok=True)

moved = []
skipped = []
for item in os.listdir(old_dir):
    src = os.path.join(old_dir, item)
    dst = os.path.join(new_dir, item)
    if os.path.exists(dst):
        skipped.append(item)
    else:
        shutil.move(src, dst)
        moved.append(item)

print(f'MOVED:{len(moved)} SKIPPED:{len(skipped)}')
if moved:
    print('moved: ' + ', '.join(moved))
if skipped:
    print('skipped (already exists): ' + ', '.join(skipped))
"
  • NO_OLD_DIR → "이동 대상 없음 (.claude/ralph-x-runs/ 없음)"
  • MOVED:N SKIPPED:M → 결과 출력 후 ".claude/ralph-x-runs/를 삭제할까요?" 확인. 승인 시 rm -rf .claude/ralph-x-runs

Read the full file on GitHub · 169 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. 10d ago First seen · 169 lines · 15 tokens per session scan C 81eee4904d25

Subscribe to this mod's changes

update-ralph-x is a skill published in the GitHub repository kangraemin/ralph-x (3 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,304 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.