Instructions for reading saved SiFR capture files, which are structured snapshots of web pages containing their content, layout, styles, and interactive elements.

Use it to analyze a saved SiFR JSON file, find important page elements, inspect layout relationships, and run prepared jq queries against the capture.

A full web-page capture can be large and hard to read directly. These instructions show how to start with its summary and inspect detailed sections only when needed.

sifr — Skill for Claude Code by e2llm/e2llm-sifr

Install

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.

Any agent

npx skills add e2llm/e2llm-sifr --skill sifr

Clone the repo

git clone --depth 1 https://github.com/e2llm/e2llm-sifr

Made for: Claude Code.

Or install e2llm, the plugin that ships this one along with the rest of its 2 skills, 2 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/e2llm/e2llm-sifr/sifr/github.svg)](https://agentmods.dev/skills/e2llm/e2llm-sifr/sifr)

Your own site

<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.

Your own site · 80×15

<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>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,553 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.5	$0.00036	$0.00621
Sonnet 5.5	$0.00018	$0.00311
Haiku 4.5	$0.00009	$0.00155

Measured 2mo ago against content hash 6df05f8b3c84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/sifr/SKILL.md · 120 lines

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 in DETAILS[level][tag][id].selector.

Read the full file on GitHub · 120 lines

Files

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.

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.

2mo ago First seen · 120 lines · 89 tokens per session scan A 6df05f8b3c84

Subscribe to this mod's changes

sifr is a skill published in the GitHub repository e2llm/e2llm-sifr (7 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,553 once invoked, about $0.0004 per session on Opus 5.5. 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.

Browser automation LLM e2llm mcp mcp-server sifr

sifr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sifre2llm/e2llm-sifr	Skill	7	2mo ago	MIT	A	89	Claude Code
application-testingAryan-Jhaveri/mcp-statcan	Skill	8	11d ago	MIT	A	190	Claude Code, Codex
scraperapi-n8nscraperapi/scraperapi-skills	Skill	10	3mo ago	MIT	A	279	Claude Code
scraperapi-cliscraperapi/scraperapi-skills	Skill	10	3mo ago	MIT	A	262	Claude Code
scraperapi-scraper-builderscraperapi/scraperapi-skills	Skill	10	3mo ago	MIT	A	206	Claude Code
scraperapi-zapierscraperapi/scraperapi-skills	Skill	10	3mo ago	MIT	A	208	Claude Code
scraperapi-datapipelinescraperapi/scraperapi-skills	Skill	10	3mo ago	MIT	A	185	Claude Code