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 e2llm/e2llm-sifr --skill sifrgit clone --depth 1 https://github.com/e2llm/e2llm-sifrWrote 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/e2llm/e2llm-sifr/sifr)<a href="https://agentmods.dev/skills/e2llm/e2llm-sifr/sifr"><img src="https://agentmods.dev/badge/skills/e2llm/e2llm-sifr/sifr/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/e2llm/e2llm-sifr/sifr"><img src="https://agentmods.dev/badge/skills/e2llm/e2llm-sifr/sifr.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 | $0.00089 | $0.01553 |
| Opus 5 | $0.00044 | $0.00776 |
| Sonnet 5 | $0.00018 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
sifr 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read a saved SiFR capture
SiFR (Single-File RAG, "see-far") is a structured snapshot of a web page: DOM structure,
interactive elements, styles, spatial layout and relationships, in a form built for a
language model to read. A saved capture is one JSON object keyed by ====SECTION====
markers.
This skill is for files. For driving a live browser, that is the e2llm skill.
Reading strategy
Step 1 — read the map. Always, and it is roughly 10–15% of the file:
jq '{meta: ."====METADATA====", summary: ."====SUMMARY====", high_nodes: ."====NODES====".high}' capture.json
That gives page context, every interactive element, layout clusters, structural patterns and the tree of important nodes — enough to understand the page and plan what to look at next.
Step 2 — drill in on demand. Read DETAILS, RELATIONS, or NODES.med / NODES.low
only when you need a specific element's selector, styles or spatial context. They are large
and most questions do not need them.
Ready-made queries for both steps: references/jq-recipes.md.
Question-led examples: use-cases.md.
Sections
| Section | Key | Contains |
|---|---|---|
| METADATA | ."====METADATA====" |
url, viewport, version, stats (node counts, salience distribution, preset), stateAgeMs |
| SUMMARY | ."====SUMMARY====" |
interactive elements by category, layout clusters, structural patterns, page styles |
| NODES | ."====NODES====" |
tree: {high,med,low}.{tag}.{id} with parent, children, cluster, pattern |
| RELATIONS | ."====RELATIONS====" |
spatial (above/leftOf/overlaps) + ARIA (labelFor/describedBy/controls) |
| DETAILS | ."====DETAILS====" |
per-element: selector, text, attributes, styles, layout, hints |
Block order in the document is METADATA → SUMMARY → NODES → RELATIONS → DETAILS. The front-loading is deliberate: what matters most comes first, so reading can stop early.
ID system
#foo— a real DOM ID, usable as a CSS selector directly.btn001,a042,div003— compact SiFR-assigned IDs. Look up the real CSS selector inDETAILS[level][tag][id].selector.
What ships with it
2 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.
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 · 120 lines · 89 tokens per session scan A 6df05f8b3c84
sifr is a skill published in the GitHub repository e2llm/e2llm-sifr (6 stars, last pushed 7d ago), licensed MIT. It adds 89 tokens to every session and 1,553 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
scraperapi-n8n
Generate n8n workflows that use the official ScraperAPI community node (n8n-nodes-scraperapi-official). Use this skill whenever the user wants to build, design, automate, or scaffold an n8n workflow that scrapes the web through ScraperAPI — even when they don't say "skill" or "ScraperAPI node" by name. Triggers…
scraperapi-cli
Product-usage reference for the official ScraperAPI command-line tool (sapi, distributed as scraperapi-cli). Use this skill whenever the user wants to scrape, run async jobs, fetch structured data, manage crawls, check account credits, or drive DataPipeline projects from a terminal or shell script — anywhere a…
scraperapi-scraper-builder
Build and implement web scrapers using ScraperAPI. Use this skill whenever the user asks to build, write, create, or implement a scraper, or wants runnable code that extracts data from a website. Trigger on: "build me a scraper for [website]", "write a scraper that fetches product pages from [ecommerce site]", "I need…
scraperapi-zapier
Guide users to build Zaps that use the official ScraperAPI Zapier integration. Use this skill whenever the user wants to add web scraping, SERP data, or e-commerce data to a Zapier workflow through ScraperAPI — even when they don't say "skill" or name the integration. Triggers include: "build a Zap that scrapes Amazon…
scraperapi-datapipeline
Product-usage reference for ScraperAPI's DataPipeline — managed, scheduled scraping projects that run automatically and deliver results to a webhook or dashboard download. Consult when the user needs recurring scraping, has a large list of URLs/ASINs/queries to process, or wants to avoid building and maintaining their…
scraperapi-research-agent
Autonomous web research agent — takes a research question, uses ScraperAPI to discover and scrape relevant sources, uploads content as file artifacts to the Anthropic Files API, then feeds everything to Claude for synthesis into a cited research report. All in one flow. Use when user asks: "research X for me and give…