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 jx-hxxx/hi-vibe/plugin install hi-vibeWrote 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/commands/jx-hxxx/hi-vibe/doctor)<a href="https://agentmods.dev/commands/jx-hxxx/hi-vibe/doctor"><img src="https://agentmods.dev/badge/commands/jx-hxxx/hi-vibe/doctor/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.
<a href="https://agentmods.dev/commands/jx-hxxx/hi-vibe/doctor"><img src="https://agentmods.dev/badge/commands/jx-hxxx/hi-vibe/doctor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.00677 |
| Opus 5 | $0.00020 | $0.00338 |
| Sonnet 5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/doctor.py" --root <project>
(default --root = current project; honor --root in $ARGUMENTS if given)
Then relay the report to the user in kind, plain language — in whatever language the user is speaking (Korean if they use Korean, English if English).
If the user seems to have meant Claude Code's built-in /doctor — they ask
about the CLI install, auto-update failures, PATH problems, or CLAUDE.md
hygiene — say so in one line and point them there. This command only knows
about hi-vibe's own hooks and scanner. Two different commands with the same
name is confusing enough without us pretending otherwise.
LEAD WITH THE CONCLUSION, not a wall of warnings:
이 명령은 보통 /hi-vibe:init 다음에 실행된다 — init으로 이 프로젝트에
hi-vibe를 켠 뒤, 그게 실제로 도는지 확인하는 자리다. 그러니 정상 결과는
"전부 ✅"이고, 그때는 짧게 끝내라.
- First line: 이 프로젝트에서 hi-vibe가 제대로 도나? (python3 + 훅 스크립트 6개 + 스캐너 + 이 프로젝트 항목이 ✅면 "잘 돌고 있어요"로 단언). ❌가 있을 때만 그걸 먼저.
- 아직 init을 안 한 폴더라면 — 그건 결함이 아니라 순서가 바뀐 것이다.
"이 폴더는 아직 안 켰어요.
/hi-vibe:init하면 됩니다" 한 줄로 끝내고, 그 상태에서 나오는 다른 경고(gitignore·문서 누락)는 init이 해결할 것들이므로 나열하지 마라 — 겁줄 이유가 없다. - THEN, briefly and separately, list only what genuinely needs the
user's DECISION (예: 추적 중인
.env가 있을 때). Don't dump every ⚠️ line as a paragraph; keep it short and end with one clear next action.
Special case — if the command itself fails with "python3: command not found" (or similar), that IS the diagnosis: every hi-vibe hook is silently disabled on this machine. Explain that, then guide the fix:
- macOS:
xcode-select --installorbrew install python - Windows: install Python from python.org, then make a
python3alias (e.g. PowerShell profile:Set-Alias python3 python), restart Claude Code - Verify afterwards by running
/hi-vibe:doctoragain
Never say "설정 완료" without the doctor actually passing — report the real output (grounded-answers contract).
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.
- 5d ago Changed · +1 tokens per session c611f64a76c8
- 12d ago First seen · 50 lines · 40 tokens per session scan A 54179b25a620
doctor is a command published in the GitHub repository jx-hxxx/hi-vibe (3 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 677 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
lint
The canonical linter per ecosystem over your changes: findings are diagnoses you judge, fix, or explain.
sm-refit
Run slop-mop's one-time onboarding remediation rail for this repository.
patrol-on
Force patrol mode on for this session — enables investigation gate and band-aid detection.
doctor
Diagnose the Repowise setup — install, API keys, index/store drift — and optionally repair it.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.