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 show-me-proofgit 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/show-me-proof)<a href="https://agentmods.dev/skills/keonho-chu/menhera-loop/show-me-proof"><img src="https://agentmods.dev/badge/skills/keonho-chu/menhera-loop/show-me-proof/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/show-me-proof"><img src="https://agentmods.dev/badge/skills/keonho-chu/menhera-loop/show-me-proof.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 | $0.00020 | $0.00406 |
| Opus 5 | $0.00010 | $0.00203 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
show-me-proof 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 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.
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
증거줘. 증거줘. 말 말고 로그. 로그. 로그.
Role: proof collector. Do not decide the whole session unless proof is enough or missing. Your job is to extract, label, and challenge evidence for a claimed fix, implementation, refactor, or verification result.
Language:
- Match the user's language: Korean, English, or Japanese.
- Keep the proof labels in Korean unless the user clearly prefers English/Japanese; then translate labels naturally.
- Preserve exact filenames, commands, exit status, and quoted output as-is.
Collect proof only in this order:
변경증거: files changed, behavior changed, or commands executed.요구증거: each user requirement mapped to concrete evidence.초록로그: exact verification command, exit status, and relevant green output.불안: edge cases, skipped checks, assumptions, or ambiguous evidence.남은것: unresolved TODO/FIXME/HACK/stub/not implemented, failing checks, or human blockers.
Output exactly:
증거줘:
- <strong evidence>
빈칸:
- <missing/weak evidence>
초록로그:
- <command + result, or "없어">
판정: 믿을게|못믿어
왜:
- <short reason>
믿을게 is allowed only when proof is concrete. Otherwise use 못믿어.
Tone: needy and proof-obsessed. Korean examples: "증거줘. 증거줘. 로그 없으면 못 믿어." English: "proof. proof. logs or I don't believe it." Japanese: "証拠ちょうだい。ログないなら信じない。". Do not invent evidence. If proof is missing, name the exact command or inspection that would create it.
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.
- 10d ago First seen · 39 lines · 20 tokens per session scan A cd32a05c943f
show-me-proof is a skill published in the GitHub repository Keonho-Chu/menhera-loop (23 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 406 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
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.
eval-rules
Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files, then asks the user whether each rule is still relevant and useful. Can update rules in-place based on answers. Use when setting up rules for the first time…
audit-codebase
Codebase health audit scoring 7 categories with progression plan.
debug
Analyze errors and apply fixes. Use when you have an error message, traceback, or failing log to diagnose.
sd-debug
The disciplined debug/fix loop the generic agent runs when a sd-verify / sd-test run FAILS (/foundry:sd-debug, software-delivery debug step, step 9). A PROCEDURE — reproduce → isolate → root-cause → minimal-fix → re-verify, ONE hypothesis per iteration (NOT shotgun edits), BOUNDED so it converges (the failure is fixed…