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.
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/plugins/fledgeling-co/fledgeling-plugins/eli5)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/eli5"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/eli5/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/plugins/fledgeling-co/fledgeling-plugins/eli5"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/eli5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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 — 10 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "eli5",
"description": "Build an interactive, self-contained HTML explainer that makes a hard idea genuinely click - a thing you operate, not a document you read. Lets the mechanism pick the shape of the page from eight that recur (Machine, Field, Solid, Ladder, Fork, Trace, Assembly, Reveal) rather than giving every topic the same tabs, and commits to a palette and type pairing of its own. Grounded in the cognitive science of how people form mental models: a structure-mapping analogy carrying the boundary where it stops being true, a Predict-Observe-Explain beat where the reader commits a guess before the reveal, and readouts inside the diagram rather than beside it. Inlines Three.js when a flat projection loses the invariant, GSAP when a state change moves several things in order or a Reveal scrubs on scroll, a Remotion-rendered clip when the sequence is too expensive to compute live, and generated imagery from media-gen-pro - all embedded, never from a CDN. Fails the build on an artifact that draws with SVG and CSS alone unless the choice is declared, since four in a row did. Ships a scaffold that wires the theme tokens, reduced-motion path, markers and libraries in one command, fetching each library once from a pinned checksummed URL rather than a CDN the reader would load. Routes charts through the dataviz skill first. A deterministic linter fails the build on external assets, missing viewBox, uncaptured pointer drags, leaked animation frames, motion with no reduced-motion path, buried analogy limits, absent prediction beats, thin visuals, single-mode interaction, prose over budget, condescending register and copied template headings. Use for \"/eli5 <topic>\", \"explain how X works\", \"make me an explainer for Y\", \"I still don't get Z\". Names its reader as a curious sixteen-year-old rather than a peer, and fails the build on a topic-specific term used without a definition - the failure a baby-talk detector cannot see - on placeholder nouns anWhat it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 327 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago Changed ba4a6ca76043
- 1mo ago Changed 9592782d1331
- 1mo ago First seen · 10 lines scan A 876247b3ee4b
eli5 is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
edulab
A collection of educational skills that turn school subject questions into interactive teaching webpages. It covers 3D geometry, analytic geometry, conic sections, and chemical reactions.
master-skill
A collection of Buddhist AI assistant skills based on Buddhist texts and commentaries, covering teachers and traditions from India, China, Tibet, and Theravāda Buddhism.
explainer-video
Short explainer videos made with ManimCE, narrated when the speech plugin is installed and silent otherwise. The produce skill plans the beats, writes one scene script whose scene changes follow the narration's word timings, renders at low quality first, muxes narration and captions with ffmpeg, and checks every…
hypha
Hypha is the AI agent of the Mycelium ecosystem: a connecting filament between engineers and the SysML v2 specification. Provides skills and subagents for KerML/SysML v2 metamodel lookup, standard model library lookup, normative spec citation, and SysML v2 textual-notation validation.
understanding
Understand a topic, a bug, or a Claude Code workflow: minimal explanations, root-cause diagnosis, execution traces.
awesome-japanese-nlp-slides marketplace
Search tools for awesome-japanese-nlp-slides: find Japanese NLP presentation slides and lecture materials.