perihbahasa

perihbahasa is a skill for Claude Code from widnyana/eyay-toolkits. It costs 111 tokens per session (3,216 once invoked), scanned A, original, MIT.

A generator for humorous Indonesian twists on traditional proverbs, including wordplay, reversals, rhymes, and flirty or emotional captions.

In plain words
What is it for?
Use it when asking for a perihbahasa, a proverb pun or remix, a funny or flirty Indonesian saying, or a caption based on an idiom.
Why use it?
It helps turn familiar sayings into lines that express pain, disappointment, insecurity, romance, or absurd humour in a culturally recognisable form.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the perihbahasa plugin — 1 skill shipped together

Good fit Use it when asking for a perihbahasa, a proverb pun or remix, a funny or flirty Indonesian saying, or a caption based on an idiom.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/widnyana/eyay-toolkits/perihbahasa
Install

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.

Any agent
npx skills add widnyana/eyay-toolkits --skill perihbahasa
Clone the repo
git clone --depth 1 https://github.com/widnyana/eyay-toolkits

Made for: Claude Code.

Or install perihbahasa, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for perihbahasa

README.md
[![agentmods](https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/perihbahasa/github.svg)](https://agentmods.dev/skills/widnyana/eyay-toolkits/perihbahasa)
Your own site
<a href="https://agentmods.dev/skills/widnyana/eyay-toolkits/perihbahasa"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/perihbahasa/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.

agentmods 80×15 button for perihbahasa

Your own site · 80×15
<a href="https://agentmods.dev/skills/widnyana/eyay-toolkits/perihbahasa"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/perihbahasa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.03216
Opus 5 $0.00056 $0.01608
Sonnet 5 $0.00022 $0.00643
Haiku 4.5 $0.00011 $0.00322

Measured 11d ago against content hash b60d68d1c388, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

perihbahasa 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/merge_proverbs.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/perihbahasa/skills/perihbahasa/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perihbahasa (Peribahasa Remix — Pun, Reversal, Transplant)

Peribahasa (peri + bahasa) adalah pepatah biasa. Perihbahasa (perih + bahasa) adalah versi yang sengaja dibuat perih — dan nama plugin ini sendiri adalah contoh tekniknya: satu pergeseran bunyi (peri → perih) mengubah "kata bijak" jadi "kata yang nyeri."

Perih itu bukan luka fisik. Ingat "sakit tapi gak berdarah, gak luka" — pain yang diakui sah walau tanpa bukti fisik, karena ia luka emosional: nyesek, kecewa, campur aduk, resah, insecure. Perihbahasa yang baik tidak menciptakan luka baru — ia menyentuh luka lama yang sudah ada di pembaca tapi belum diakui, dan barisnya adalah garamnya. Teknik (Pun-Swap, Moral-Reversal, dst.) hanya kendaraannya; yang menentukan lolos-tidaknya adalah apakah baris itu menyentuh sesuatu yang sudah nyeri, bukan sekadar pintar secara teknis.

Test lolos: akankah pembaca screenshot lalu kirim ke teman dengan caption "literally me" atau "kena banget" — bukan cuma "lucu juga"? Kalau jawabnya cuma "clever," itu plesetan, bukan perihbahasa. Lihat Anatomy #1 dan #11 di bawah untuk detail.

Target imitasi: references/exemplars.md — baris gold-standard, dikelompokkan per teknik dan diberi tag perih vs plesetan. Baca dulu, tiru kalibernya. Kalau outputmu tidak sekuat contoh di sana, buang dan ulang.

Anatomy — kenapa sebuah perihbahasa nendang

  1. Perih, bukan sekadar pintar. Sebelum menilai teknik/rima, tanyakan: luka apa yang sudah ada di pembaca yang disentuh baris ini? Kalau tidak ada luka yang tersentuh — hanya lelucon pintar tanpa sengatan — itu plesetan (boleh, tapi bukan target utama), bukan perihbahasa sejati.
  2. Pun-nya adalah maknanya, bukan dekorasi. Kata yang ditukar harus membawa argumen nyata. nila → async works karena async memang "hal kecil yang merusak sistem besar."
  3. Mainkan moral aslinya — sering dengan membaliknya. Pertahankan moral di domain baru, atau balik untuk membongkar kebenaran yang ditutupi peribahasa aslinya.
  4. Relatable = spesifik, bukan vibe. Sebut satu momen betulan (jadian seminggu, move-on sedasawarsa), bukan ringkasan generik ("sedih karena di-ghosting").
  5. Asimetri emosional = mesin yang dipakai ulang. Sebab kecil : akibat besar, atau investasi besar : hasil kecil — diselipkan ke kerangka se-… se-….
  6. Tukar kata bedah, bukan tulis ulang klausa. Makin sedikit kata diganti, makin keras "aha"-nya. terbitlah terang → terdengarlah erang; jatuh → jauh; payung → kamu.
  7. Jaga kerangka fonetik via near-homophone. jatuh→jauh, terang→erang, beriak→teriak, tangan→kenangan. Suara bertahan walau makna berbalik.
  8. Pilih bentuk yang pas untuk lawakannya — lihat katalog Techniques; jangan paksa satu bentuk untuk semua idiom.
  9. Nada itu kerajinan; menjelaskan membunuhnya. Budaya curhat online Indonesia (GenZ/ milenial) menyampaikan pain lewat deadpan — nada datar, self-deprecating, tanpa drama — karena itulah cara yang "aman" secara sosial untuk mengaku vulnerable tanpa terlihat caper/cari perhatian. Menjelaskan lelucon merobek armor itu dan berubah jadi curhat sungguhan yang minta dikasihani — canggung. ALL-CAPS adalah satu-satunya pengecualian (amarah yang diperagakan, bukan mentah). Jangan pernah jelaskan lelucon.
  10. Domain = rasa sakit yang kamu aktifkan. Jangkau domain kehidupan GenZ/milenial Indonesia sehari-hari, online maupun offline — lihat daftar lengkap di bawah. Pilih yang punya derita betulan, bukan tema kabur.
  11. Bobot budaya menguatkan. Plesetin baris yang dihafal semua orang Indonesia (Habis gelap terbitlah terang, Berakit-rakit ke hulu, Harimau mati…, Karena nila setitik…).

Read the full file on GitHub · 172 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 172 lines · 111 tokens per session scan A b60d68d1c388

Subscribe to this mod's changes

perihbahasa is a skill published in the GitHub repository widnyana/eyay-toolkits (7 stars, last pushed 8d ago), licensed MIT. It adds 111 tokens to every session and 3,216 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

google-ads-assets

Plan, validate, and safely publish Google Ads assets, including sitelinks, callouts, structured snippets, image assets, and Performance Max asset briefs. Use when asked for Google Ads assets, ad extensions, sitelinks, callouts, snippets, image assets, Performance Max assets, PMax creative, or an asset audit.

nowork-studio/notfair-plugin · 72 tokens

meta-ads-creative

Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.

nowork-studio/notfair-plugin · 59 tokens

paid-ads-creative

Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines, creative fatigue, asset ideas, or a creative refresh.

nowork-studio/notfair-plugin · 52 tokens

paid-ads-tiktok

Plan and review TikTok Ads creative experiments with measurement, rights, and conversion guardrails. Use for TikTok advertising, Spark Ads, short-form video ads, creator briefs, TikTok campaign setup, or TikTok performance exports.

nowork-studio/notfair-plugin · 52 tokens

meta-ads-creative

Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.

nowork-studio/notfair-plugin · 59 tokens

remove-ai-marks

Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…

ShadowAqueduct/watermark-remover · 135 tokens