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 agentmods add skills/dzhng/duet-agent/eli5npx skills add dzhng/duet-agent --skill eli5git clone --depth 1 https://github.com/dzhng/duet-agentWrote 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/dzhng/duet-agent/eli5)<a href="https://agentmods.dev/skills/dzhng/duet-agent/eli5"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/eli5.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00687 |
| Opus 5 | $0.00015 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
eli5 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 4d 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.
This is a copy
100% identical to eli5 — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ELI5
Turn the referenced spec or change into an accurate mental model for a technical reader who does not live in the code. Plain language, full precision: simplify the telling, never the claims.
The Register
Other skills point here when their output must be readable by someone who didn't live the work. The reader is technical — pseudocode and precise claims land fine — but they have read none of the code and none of the session's messages: no diff, no transcript, no labels the work invented along the way. Writing ELI5 means:
- Walk one concrete scenario end to end — the triggering event, what happens today, what the change (or the unbuilt alternative) would do — instead of describing properties in the abstract.
- Define every term of art at first use; never lean on labels the spec, code, or session invented.
- Use small concrete examples without replacing precise claims with analogies.
- Reach for pseudocode when explaining control flow, ordering, or timing. Prose describing when-something-fires reads as plausible and hides the gap; five lines of pseudocode make the gate visible and let the reader see the case you missed. Write it at the level of the decision, not the implementation — the conditions and their order, not real function signatures. The tell that you needed it: your prose contains "only when", "before", "unless", or "as soon as" and the reader still cannot say what happens on the second call.
- The test: the text stands alone, without the diff, the spec, or the transcript. If the reader must ask "explain this part", it failed.
Workflow
- Read the complete referenced artifact and inspect current owners when the spec alone cannot establish behavior. When no artifact is named, explain the session's current change (working tree or branch diff). Separate what exists today from what is only proposed.
- Explain the problem through its user or operational consequence, including why the current design produces it.
- Explain the solution as one simple before/after data flow. Introduce each component by responsibility, not by filename or internal symbol.
- Inventory schema and durable-contract changes exhaustively: added, changed, removed, reset, and deliberately unchanged. Include cursor or wire-format cutovers when they affect stored data or readers. Say explicitly when there are no schema changes.
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.
- 4d ago First seen · 73 lines · 29 tokens per session scan A 268c996bcc62
eli5 is a skill published in the GitHub repository dzhng/duet-agent (42 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 687 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to eli5, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
evaluator-write-qa
Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.
evaluator-review-contract-parallel
Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
evaluator-write-final-parallel
Internal Auto-Harness evaluator skill for parallel final QA report aggregation. Use only inside the Evaluator subagent during evaluatorfinalparallel.
evaluator-write-qa-parallel
Internal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evaluator subagent during evaluatorqaparallel.
evaluator-write-retest-parallel
Internal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside the Evaluator subagent during evaluatorretestparallel.