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/skills/jx-hxxx/hi-vibe/repo-xray)<a href="https://agentmods.dev/skills/jx-hxxx/hi-vibe/repo-xray"><img src="https://agentmods.dev/badge/skills/jx-hxxx/hi-vibe/repo-xray/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/skills/jx-hxxx/hi-vibe/repo-xray"><img src="https://agentmods.dev/badge/skills/jx-hxxx/hi-vibe/repo-xray.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 | $0.00165 | $0.03147 |
| Opus 5 | $0.00082 | $0.01573 |
| Sonnet 5 | $0.00033 | $0.00629 |
| Haiku 4.5 | $0.00016 | $0.00315 |
Grade A, and why
repo-xray 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 12d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-xray
A repo evidence engine: a script produces machine evidence, and you turn that evidence into short, kind, actionable advice. The reader may be new to coding — plain words, no tool jargon, at most three suggestions at a time unless they ask for a full report.
NO STRUCTURAL CLAIM WITHOUT RUNNING THE SCRIPT
NO ABSENCE CLAIM WITHOUT STATING THE SCAN RANGE
A DEAD "CANDIDATE" IS NOT A VERDICT
If you have not run the script in this session, do not state counts ("unused functions: 12") or absence ("that function doesn't exist"). Run it first, read the JSON, then make the smallest true claim the evidence supports. Cross this line and the tool becomes a confident guesser — exactly the failure it exists to prevent.
Commands
Run from anywhere; point --root at the repo being analyzed.
# Full structure scan -> writes <root>/.repo-xray/report.json
python3 <skill-path>/scripts/audit.py scan --root <repo>
# "Does X exist anywhere?" -> exact hits + similar names, prints JSON
python3 <skill-path>/scripts/audit.py find <name> --root <repo>
<skill-path> is this skill's directory — in plugin installs that is
${CLAUDE_PLUGIN_ROOT}/skills/repo-xray. The scan needs only Python 3
(stdlib) — no installs. Suggest adding .repo-xray/ to .gitignore
once, the first time a scan runs in a repo.
실행 시간 — 느린 것 ≠ 멈춘 것
스캔은 저장소 크기에 따라 수 초에서 수십 초가 걸린다(함수가 많으면
near-duplicate 비교가 가장 오래 걸린다). 이건 정상이다. 짧은 타임아웃으로
끊고 다시 돌리지 마라 — 죽은 줄 알고 재실행하면 프로세스만 겹쳐 쌓여
머신이 포화되고 오히려 더 느려진다(관측된 실패 모드다). 오래 걸릴 것 같으면
한 번만 백그라운드로 돌리고 완료를 기다린 뒤 report.json을 읽어라.
스캔은 끝나면 항상 리포트를 쓰므로, 리포트가 없으면 "아직 도는 중"이지
"고장"이 아니다. near_duplicate_scan_truncated: true가 보이면 near-dup만
시간 상한에 걸려 일부 생략된 것이고, 나머지 결과는 완전하다.
Which command for which question
- "중복 코드 있어?", "정리할 것 알려줘", "구조 어때?", "안 쓰는 코드?"
→
scan, then readreport.json. - "X라는 함수/기능 이미 있어?", "어디서 쓰여?" →
find X. If the user describes a behavior rather than a name ("환율 바꾸는 거"), runfindon 2-3 plausible names (e.g.exchange,usd_to_krw,convertRate) and also checksimilar_symbol_namesin the output. - Before writing a new helper the repo might already have →
findfirst.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 211 lines · 165 tokens per session scan A 0b896838615d
repo-xray is a skill published in the GitHub repository jx-hxxx/hi-vibe (3 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 3,147 once invoked, about $0.0008 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 skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
fidelity-gate
Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.