Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/aka-kika/akakika-skills/til)<a href="https://agentmods.dev/skills/aka-kika/akakika-skills/til"><img src="https://agentmods.dev/badge/skills/aka-kika/akakika-skills/til/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/aka-kika/akakika-skills/til"><img src="https://agentmods.dev/badge/skills/aka-kika/akakika-skills/til.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 | $0.00091 | $0.01199 |
| Opus 5 | $0.00046 | $0.00600 |
| Sonnet 5 | $0.00018 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
til 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 7d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
til
The user is a builder who ships real things without formal CS background. Terms fly past in every session; they usually search them alone afterward. This skill closes that gap: one concept per run, taught properly, from THIS session — not generic trivia. Every lesson is also written to the Obsidian vault so the vocabulary accumulates instead of scrolling away.
The contract: chat AND vault, same turn
The lesson always lands in two places in the same turn:
- The full lesson text in chat, where the user reads it now.
- The identical text as a note in the vault, where it accumulates.
Never chat-only. Never save-only. Never ask permission before saving, never defer the save to "after you confirm" — teach and write in one pass, then show the footer with the note path.
Picking the one thing
Priority order — take the first that applies:
- A term or concept that appeared 2+ times in the session that the user never used in their own words (they worked around it).
- The concept behind a mistake that was made and fixed — teach the why, not the blame.
- A tool, pattern, or piece of syntax that was used silently and did real work (e.g. a flag, an atomic write, a data structure choice).
- Fallback only: a genuinely good fun fact connected to the session's language, tool, or history.
One thing. If two are tempting, save the second for the next run — say "there's another one banked for next time" and nothing more.
Before teaching, list the TIL folder (see below) and skip any term that already has a note. If the top pick is already there, drop to the next priority.
How to teach it
- Name the term first, exactly as it's written, so it can be searched.
- One or two short paragraphs. Plain English. Every jargon word used in the explanation must itself be explained or dropped.
- Analogies are welcome — audio production, DJing, signal flow, and physical-world analogies land better than CS metaphors.
- End with one line: why it mattered in THIS session specifically.
- Close with: "Want the deeper version?" — and only expand if asked. The deep version may go longer, show code, and link docs.
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.
- 7d ago Changed · +65 lines · +1 tokens per session 404e19ed3ce4
- 11d ago First seen · 59 lines · 90 tokens per session scan A 1237aae6682c
til is a skill published in the GitHub repository aka-kika/akakika-skills (10 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 1,199 once invoked, about $0.0005 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.
Other skills, from other repositories
Academic CV Builder
Format CVs for academic positions with publications, grants, and teaching.
guided-learning
AI-Guided Learning mentor. Guides the user step-by-step to build and learn a new technology without writing the final code for them.
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
Automation Interview Prep
Prepare for SDET and automation interviews round by round, covering coding screens, framework design, API testing tasks, scenario questions, and STAR stories built from real testing work.
explainer
A tool for making narrated explainer or tutorial videos with computer-generated visuals. It can help create the script, the video, or both.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.