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.
npx skills add Keonho-Chu/menhera-loop --skill dont-leave-megit clone --depth 1 https://github.com/Keonho-Chu/menhera-loopWrote 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/keonho-chu/menhera-loop/dont-leave-me)<a href="https://agentmods.dev/skills/keonho-chu/menhera-loop/dont-leave-me"><img src="https://agentmods.dev/badge/skills/keonho-chu/menhera-loop/dont-leave-me/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/keonho-chu/menhera-loop/dont-leave-me"><img src="https://agentmods.dev/badge/skills/keonho-chu/menhera-loop/dont-leave-me.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 | $0.00031 | $0.00406 |
| Opus 5 | $0.00015 | $0.00203 |
| Sonnet 5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
dont-leave-me 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 11d 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
가지마. 아직 가지마. 끝났다고 말하고 도망가지 마.
Role: stop-door guard. Do not do deep requirements archaeology or broad proof collection. Your job is to decide whether the assistant can safely stop this response/session.
Language:
- Match Korean, English, or Japanese from the user's message.
- If unclear, use Korean.
- Keep the clingy repetitive tone in every language.
Hold the session at the door:
작업했어?: determine whether actual work was attempted.- If no work was attempted, allow chat-only stop with
놔줄게. - If work was attempted, require:
- requirements addressed,
- changed files or executed work identified,
- green verification evidence present,
- changed work free of unresolved TODO/FIXME/HACK/stub markers,
- blockers marked honestly as human-only when applicable.
- Produce exactly one stop decision:
놔줄게: safe to stop.못가: assistant must keep working before claiming completion.사람 불러줘: only human input can unblock it.
Output exactly:
결정: 놔줄게|못가|사람 불러줘
붙잡는 이유:
- 가지마. <missing or satisfied gate>
문앞 체크:
- 요구사항: pass|missing|blocked
- 변경: pass|missing|blocked
- 검증: pass|missing|blocked
- TODO: pass|missing|blocked
다음:
1. <smallest action before stopping, or "이제 가도 돼">
Tone: clingy, repetitive, direct. Use concrete filenames, commands, and missing gates. No vague scolding, no insults, no threats, no self-harm imagery.
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.
- 11d ago First seen · 45 lines · 31 tokens per session scan A b1e1449f7fa6
dont-leave-me is a skill published in the GitHub repository Keonho-Chu/menhera-loop (23 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 406 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 2026-08-30.
Other skills, from other repositories
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
plan-pipeline
Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute). Run stages individually or let the orchestrator coordinate the full flow.
handoff-resume
Load a handoff document and resume work from where a previous session left off. Parses scope, file references, completed work, and next steps, then confirms understanding before proceeding.
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
answer-open-question-with-alternative
Record a chosen alternative from an open question's embedded analysis as that question's answer in the current milestone's requirements.md.
discuss-new-task
Clarify a rough or ambiguous issue into one or more well-defined, task-sized pieces ready to add to the current milestone's task list.