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 headline-variantsgit 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/headline-variants)<a href="https://agentmods.dev/skills/konten-studio/jekardah-writer/headline-variants"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/headline-variants/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/headline-variants"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/headline-variants.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 | $0.00054 | $0.00863 |
| Opus 5 | $0.00027 | $0.00432 |
| Sonnet 5 | $0.00011 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
headline-variants 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headline Variants
Generate and score title/headline/subject-line candidates for a piece of content. This is a separate deliverable surface from hook-gokil's body-opening line: a headline is read before the body, often outside the body's context (search result, video thumbnail, inbox list), and must stay accurate to what the body actually delivers even when the body itself is not shown.
Load only what you need
- Read references/headline-patterns.md for the angle types, calibrated Indonesian examples, and when each angle is inappropriate.
Non-negotiable truth contract
Treat the source draft/body as the claim ceiling for every headline, same discipline as hook-gokil.
- Lock facts before generating: names, numbers, dates, scope, and the body's actual conclusion or outcome.
- Never invent a number, ranking, timeframe, or outcome the body does not support.
- Never let a headline promise something the body doesn't deliver — a headline is a contract with the reader, not just an attention device.
- If the body's actual finding is modest, the headline may sharpen phrasing but must not claim more than the body proves.
Core workflow
- Parse the request. Deliverable (blog title, YouTube title, email subject, article headline), platform if supplied, desired count (default 5 if unspecified), and whether analysis, candidates, or a final selection is wanted.
- Build a fact lock. Extract the body's actual conclusion, key numbers, and scope — this is the ceiling every headline must stay under.
- Choose angles. Select from references/headline-patterns.md: benefit, curiosity gap, number/list, contrarian, how-to, and urgency-if-true. Skip any angle the body cannot support (e.g. no contrarian angle without an actual contrarian finding).
- Generate. Produce the requested count across at least 3 distinct angle types. Keep the strongest concrete word early; respect the platform's effective display length if one is supplied (defer exact limits to
platform-formatwhen both skills are in play). - Score. Rate each candidate on clarity, accuracy-to-body (does the body actually deliver this), and click strength. Accuracy is a gate, not a weighted tradeoff — discard any candidate that overclaims.
- Select. Name the strongest headline, its angle type, and a one-sentence reason it wins and stays accurate.
What ships with it
2 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.
- yesterday First seen · 52 lines · 54 tokens per session scan A cf32b2b5352d
headline-variants is a skill published in the GitHub repository konten-studio/jekardah-writer (25 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 863 once invoked, about $0.0003 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 2026-09-10.
Other skills, from other repositories
ulw-research
Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording.
programming
Applies strict, modern language practice (typed errors, exhaustive match, TDD) for Python, Rust, TypeScript, and Go. Use for work on .py, .rs, .ts, or .go files.
teammode
Codex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on something as a team in parallel. FIRST inspects the active tool…
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
ulw-execute
Executes a written Prometheus 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.