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/fledgeling-co/fledgeling-plugins/eli5npx skills add fledgeling-co/fledgeling-plugins --skill eli5git 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/skills/fledgeling-co/fledgeling-plugins/eli5)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/eli5"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/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 | $0.00320 | $0.05618 |
| Opus 5 | $0.00160 | $0.02809 |
| Sonnet 5 | $0.00064 | $0.01124 |
| Haiku 4.5 | $0.00032 | $0.00562 |
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.
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eli5
Explaining something is not simplifying it. It is finding the one relationship the whole thing turns on, building a bridge to something the reader already owns, saying exactly where that bridge stops carrying weight, and then handing the reader the controls.
This skill builds a single self-contained HTML file that does that. Every rule traces to
a row in references/evidence.md, which carries the citations from a four-backend research
panel and marks where the panel disagreed.
Three things it refuses. It does not ship an analogy without its boundary, because an unbounded analogy is how a confident misconception gets installed. It does not ship a document with a diagram in it: the reader operates the mechanism, and prose is what is left over. And it does not write for someone who already knows.
Who is reading, and it decides everything else
A curious sixteen-year-old, or an adult who is sharp and has never worked on this. They can follow a real mechanism. They do not know your vocabulary, and they will not look anything up — they will close the page.
That has one consequence, and it is the rule the whole skill turns on: every word specific
to this topic is defined where it first appears, or replaced with a plain one. Mark each
definition with <dfn>. Definitions cost nothing against the prose budget, so there is never
a reason to leave one out.
The failure this replaces was not baby-talk. It was the opposite, and the gate could not see it — one artifact passed every check at 200 words while reading like this:
| What shipped | What the reader needed |
|---|---|
| "193 of 200 cards carry evidence that bites. Verified is a different axis." | "193 of the 200 tasks now have a test behind them. That was never what was blocking us." |
| "which classes to add, each one's oracle, and the closure count with its window" | "which kinds of bug to look for, how you would know you had found one, and how long to watch" |
| "every class at rung zero · coverage 65.9%" | "no category has got past the first of four levels. Two thirds of the code is watched." |
What ships with it
10 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.
- gemini.md 19 KB
- references/artifact-engineering.md 14 KB
- references/evidence.md 33 KB
- references/forms.md 8.6 KB
- references/motion-and-media.md 9.3 KB
- references/pedagogy.md 9.4 KB
- scripts/embed_media.py 4.6 KB runs code
- scripts/lint_explainer.py 45 KB runs code
- scripts/new_explainer.py 7.6 KB runs code
- scripts/vendor_lib.py 6.4 KB runs code
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 · 398 lines · 320 tokens per session scan A 1f6f6694e205
eli5 is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 320 tokens to every session and 5,618 once invoked, about $0.0016 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.