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 hook-gokilgit 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/hook-gokil)<a href="https://agentmods.dev/skills/konten-studio/jekardah-writer/hook-gokil"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/hook-gokil/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/hook-gokil"><img src="https://agentmods.dev/badge/skills/konten-studio/jekardah-writer/hook-gokil.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 | $0.00056 | $0.01217 |
| Opus 5 | $0.00028 | $0.00609 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
hook-gokil 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.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hook Gokil
Create cognitive dissonance without breaking the content's factual contract. A strong hook makes the audience ask "kok bisa?"; the body must answer honestly.
Load only what you need
- Read references/framework.md for the full analysis, generation, scoring, and rewrite method.
- Read references/types.md when choosing among the 15 WTF/killer hook types or three emotional pillars.
- Read references/examples.md for calibrated Indonesian examples, unsafe-to-safe repairs, and output shapes.
- Read references/provenance.md only when auditing the skill's design influences. Do not load
evals/during normal use; it contains maintainer evaluation artifacts, not operating instructions. - Use the distilled files in
references/for the framework, hook types, examples, and provenance. The private source material is intentionally not bundled with this public skill.
Non-negotiable truth contract
Treat the source draft/context as the claim ceiling.
- Lock facts before ideation: names, numbers, dates, scope, evidence level, causal direction, quotes, and stated outcomes.
- Never invent proof, precision, authority, consensus, urgency, scarcity, or personal experience.
- Never upgrade anecdote to science, correlation to causation, possibility to certainty, or one case to a universal rule.
- Use only a contradiction the body can resolve. If payoff is missing, weaken the hook or ask for evidence; do not manufacture a payoff.
- Preserve the author's factual meaning even when rewriting the whole draft.
If the user requests an unsupported claim, decline that claim briefly and offer the strongest accurate alternative. "Killer" describes attention strength, not permission to deceive.
Core workflow
- Parse the request. Identify deliverable, platform if supplied, language/register, audience, topic, desired outcome, and whether the user wants analysis, candidates, selection, a hook rewrite, or a whole-draft rewrite. Ask only when a missing fact would materially change the result.
- Build a fact lock. Separate supported facts, opinions/interpretations, unknowns, and forbidden upgrades. Preserve exact numbers unless rounding is explicitly allowed.
- Extract depth. Move from feature/topic to benefit or pain, then ask "so what?" until reaching a defensible human meaning. Do not turn a plausible scenario into an asserted event.
- Choose angles. Select 3-5 suitable types from references/types.md. Prefer variety over cosmetic paraphrases. Skip any type that requires unavailable proof.
- Generate. Unless the user specifies a count, produce 6 candidates across at least 3 types and at least 2 emotional pillars. Put the strongest concrete or disruptive words early. Write natural Indonesian; use English/code-mixing only when it matches the source or requested voice.
- Stress-test. Apply the body-payoff, fact-lock, specificity, first-words, clarity, and curiosity checks in references/framework.md. Repair or discard failures.
- Select. Score viable candidates, choose one strongest hook, name its type, and explain in 1-3 sentences why it wins and how the body pays it off. Accuracy is a gate, not a weighted tradeoff.
- Rewrite only the requested scope. If asked for one hook, do not rewrite the body. If asked for the whole draft, place the selected hook first and reshape the body so it closes the exact curiosity gap without adding claims.
What ships with it
5 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.
- 11d ago First seen · 69 lines · 56 tokens per session scan A 7c70272e621e
hook-gokil is a skill published in the GitHub repository konten-studio/jekardah-writer (25 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,217 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 2026-08-30.
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.