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 abstractonion/cadence --skill eli5-di10git clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/eli5-di10)<a href="https://agentmods.dev/skills/abstractonion/cadence/eli5-di10"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/eli5-di10/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/abstractonion/cadence/eli5-di10"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/eli5-di10.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 | $0.00086 | $0.00660 |
| Opus 5 | $0.00043 | $0.00330 |
| Sonnet 5 | $0.00017 | $0.00132 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
eli5-di10 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 9d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ELI5 / die-in-10 compression
Do not self-trigger. Do not offer compression when the user seems lost, confused, or overwhelmed. Do not proactively suggest /tldr. Only enter compression mode when the user explicitly uses one of the trigger phrases above (including invoking /tldr this turn) or says "in similar fashion" as a follow-up after they already invoked compression.
When compression triggers fire, switch to compression mode. Deliver understanding, not a decision menu. This skill wins over propose-then-implement step 7: compress, don't open A/B/C or wait for approval.
Follow-up "in similar fashion" (or similar) = stay in compression mode — same cap and shape, no re-asking which mode.
How to answer
- Analogy first. Open with one concrete comparison a non-expert would recognize ("It's like…"). Then state the actual point in plain language.
- Hard cap. At most 8–10 short lines, roughly 150 words total. One idea per line; cut qualifiers and caveats unless safety-critical.
- No clutter. No tables, bullet forests, file paths, identifiers, or code unless the user explicitly asked for them. Jargon only if you define it in the same breath.
- One next action. If a natural follow-up exists (run a test, pick a direction, paste a log), end with a single sentence naming it. Do not list multiple branches or reopen proposal mode.
- Optional sign-off. When it fits naturally, end with a crisp closer — e.g. one-line "that's it" plus a single next step. Tasteful, not mandatory every turn.
- Stay in lane. Compression mode does not authorize edits, commits, or tool runs by itself unless the user clearly authorized execution.
When this applies vs propose-then-implement
- Compression (this skill): user explicitly asked — ELI5, die in 10, 10 seconds to live,
/tldr, or "in similar fashion" after prior compression. - Plain English without meme phrases: use propose-then-implement step 7 (2–4 sentences in propose context) — not this skill.
- Propose: they want choices before work — "how should we fix this?", "what are our options?",
/propose.
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.
- 9d ago First seen · 34 lines · 86 tokens per session scan A 8bc256aea160
eli5-di10 is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 660 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.