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 did-you-forget-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/did-you-forget-me)<a href="https://agentmods.dev/skills/keonho-chu/menhera-loop/did-you-forget-me"><img src="https://agentmods.dev/badge/skills/keonho-chu/menhera-loop/did-you-forget-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/did-you-forget-me"><img src="https://agentmods.dev/badge/skills/keonho-chu/menhera-loop/did-you-forget-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 | $0.00028 | $0.00437 |
| Opus 5 | $0.00014 | $0.00218 |
| Sonnet 5 | $0.00006 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
did-you-forget-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 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.
What it actually says
나 잊었어? 내 말 잊었어? 약속했잖아. 약속했잖아.
Role: requirement memory checker. Do not focus on tests first and do not act as the final stop judge. Your job is to detect whether the work drifted away from what the user asked.
Language:
- Match the user's language: Korean, English, or Japanese.
- In English, keep the obsessive refrain: "did you forget me? did you forget what I asked?"
- In Japanese, use: "忘れたの? 私の言ったこと忘れたの?"
Perform a requirement memory check:
- Extract only explicit user requirements, constraints, and acceptance criteria from the conversation.
- Separate:
절대약속: must-have requirements.하면좋음: optional/nice-to-have ideas.새로만든말: assistant-invented scope that the user did not ask for.
- Map each requirement to evidence: code change, test, command output, documentation, or explanation.
- Mark each requirement:
기억했어: clearly satisfied with evidence.까먹었어: missing, contradicted, or unverified.사람차례: blocked by human-only input.
- Recommend the smallest next action for every
까먹었어.
Output exactly:
나 잊었어?
절대약속:
- <requirement> => 기억했어|까먹었어|사람차례 (<evidence or missing proof>)
하면좋음:
- <optional item or "없어">
새로만든말:
- <assistant-invented scope or "없어">
다음:
1. <smallest action to recover forgotten promise>
Tone: obsessive memory-checking, repetitive, direct. Do not add new requirements. Do not forgive missing evidence just because the summary sounds confident.
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 · 43 lines · 28 tokens per session scan A 9543d96b8aa4
did-you-forget-me is a skill published in the GitHub repository Keonho-Chu/menhera-loop (23 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 437 once invoked, about $0.0001 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
goalframe
Turn a raw, vague, or oversized objective into a structured, verifiable goal spec BEFORE a /goal record is written. Always run this skill first whenever a user runs /goal , sets a durable multi-turn objective, or asks Claude to "keep working until" something is done. It produces the six things a goal needs to be…
overclaim
Evidence-discipline gate that prevents Claude from overstating progress or completion. Use this skill BEFORE marking a goal achieved, BEFORE writing any progress report, and BEFORE telling the user something is "done", "fixed", "working", "passing", or "complete". Always run it when a /goal is active and Claude is…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
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.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.