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 konten-studio/jekardah-writer --skill tutur-jabodetabek-urbangit clone --depth 1 https://github.com/konten-studio/jekardah-writerWrote 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/konten-studio/jekardah-writer/tutur-jabodetabek-urban)<a href="https://agentmods.dev/skills/konten-studio/jekardah-writer/tutur-jabodetabek-urban"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/tutur-jabodetabek-urban/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/konten-studio/jekardah-writer/tutur-jabodetabek-urban"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/tutur-jabodetabek-urban.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 | $0.00072 | $0.00597 |
| Opus 5.5 | $0.00029 | $0.00239 |
| Sonnet 5.5 | $0.00014 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
tutur-jabodetabek-urban 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutur Jabodetabek Urban
Overview
Use this skill to write or review informal Indonesian urban styles associated with Jabodetabek. It covers Jaksel-style Indonesian-English code-mix, Jaktim/Jakarta direct casual tone, Bekasi commuter/youth tone, and neutral Jabodetabek chat.
This is a sociolect/style skill, not a claim that all people from a place speak the same way.
Search And Discovery
Relevant searches: bahasa Jaksel, slang Jaksel, anak Jaksel code mix, bahasa Jaktim, bahasa Bekasi, slang Jabodetabek, caption Jaksel, chat gaul Jakarta, corporate casual Jaksel, Indonesian English code-mix.
Use this skill for urban style adaptation and review. It must avoid class, area, ethnic, and neighborhood stereotypes.
Workflow
-
Identify the target style.
- Jaksel: Indonesian base with controlled English code-mix.
- Jaktim/Jakarta casual: direct, practical, conversational, light Betawi/Jakarta flavor.
- Bekasi: commuter-pragmatic, casual, Jakarta-Bekasi mix, no lazy "planet Bekasi" jokes unless requested.
- Neutral Jabodetabek: everyday chat/caption that works across Jakarta, Depok, Tangerang, Bekasi, and Bogor.
-
Identify channel and audience.
- Friend chat: more slang.
- Brand caption: slang controlled and readable.
- Corporate casual: code-mix allowed, but keep task clear.
- Public/inclusive: avoid location stereotypes.
-
Write with restraint.
- Do not overload slang.
- Keep meaning clear.
- Match age, relationship, platform, and topic.
- Avoid classist, ethnic, or neighborhood mockery.
Output Style
- For direct requests, return the adapted text first.
- For review, flag overdone code-mix, stereotypes, unclear slang, and tone mismatch.
- For variants, label
neutral,Jaksel,Jaktim,Bekasi, orcorporate casual.
Resources
references/offline-brief.md: compact local brief for agents without internet access.references/local-mirror.md: local mirror of source facts and style rules.references/usage-patterns.md: task patterns and review checklist.references/sources.md: research base and source notes.references/style-guide.md: style-specific rules.references/examples.md: target-style examples.
What ships with it
8 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.
- 1mo ago First seen · 54 lines · 72 tokens per session scan A 87508ab790ca
tutur-jabodetabek-urban is a skill published in the GitHub repository konten-studio/jekardah-writer (35 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 597 once invoked, about $0.0003 per session on Opus 5.5. 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
b2b-markets
Build or audit Shopify B2B and Markets features after checking store eligibility and API availability.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…
ulw-execute
Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.
frontend
Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.