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 rules/yuriyenshin/confluenceimportexport/local-mirror-formatgit clone --depth 1 https://github.com/YuriyEnshin/ConfluenceImportExportWrote 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/rules/yuriyenshin/confluenceimportexport/local-mirror-format)<a href="https://agentmods.dev/rules/yuriyenshin/confluenceimportexport/local-mirror-format"><img src="https://agentmods.dev/badge/rules/yuriyenshin/confluenceimportexport/local-mirror-format.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 | $0.01248 | $0.01248 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
local-mirror-format 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Confluence Mirror — Storage Structure and Format
This rule describes the local storage format for Confluence pages exported by the ConfluencePageExporter tool. Use it to correctly read, edit, and create pages in the local mirror.
Directory Hierarchy
Pages are stored as a folder tree that mirrors the Confluence page hierarchy:
<output-dir>/
Root Page/
index.html
.id12345_7
image.png
spec.pdf
Child Page A/
index.html
.id23456_3
Child Page B/
index.html
.id34567_1
Nested Page/
index.html
.id45678_2
- Folder name = Confluence page title (filesystem-unsafe characters are replaced)
- Folder nesting = parent-child relationships between pages
- One folder = one Confluence page
Page Folder Contents
Each page folder contains three types of files:
index.html — Page Content
The index.html file contains the page body in Confluence Storage Format — the body.storage.value field from the Confluence REST API.
This is not regular HTML. Storage format is an XHTML subset with Confluence-specific namespaces and macros.
.id_ — Identity Marker
A file named like .id12345_7, where:
12345— the page identifier (pageId) in Confluence7— the page version number on the server at the time of last sync
The marker is used for:
- Stable mapping of a local folder to a Confluence page (even after renames)
- Detecting whether the page was updated on the server (version comparison)
- Conflict tracking (
LastWriteTimeUtcof the marker = timestamp of the last sync)
Marker body. The file content is a small JSON object captured at sync time:
{"title":"Original Page Title","space":"SPACEKEY"}
title— the page's original (unsanitised) title, so special characters lost in the folder name can be restored on upload.space— the key of the space the page belongs to. A Confluence page tree always lives in a single space; this records which one, so trees from different spaces can sit side by side and be synced without specifying the space each time.
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 · 153 lines · 1,248 tokens per session scan A eef9f01ba90c
local-mirror-format is a cursor rule published in the GitHub repository YuriyEnshin/ConfluenceImportExport (5 stars, last pushed 23d ago), licensed MIT. It adds 1,248 tokens to every session, about $0.0062 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 cursor rules, from other repositories
cursorrules
You are assisting with mcp-server-powerpoint, a Windows-only MCP server that drives a live PowerPoint desktop instance via COM. When using the PowerPoint MCP tools (not when editing this repo's C# source), follow these rules.
cursorrules
When the user asks about pdf tools, use pdf-tools-ai-mcp tools: extracttext, countpages, getmetadata, mergepagesdata.
cursorrules
When the user asks about pdf document, use pdf-document-mcp tools: extracttextfrompdf, convertpdftomarkdown, mergepdfs, extracttables, summarizedocument.
cursorrules
When the user asks about document comparison, use document-comparison-ai-mcp tools: comparedocuments, compareversions, storedocument, getdocument, listversions.
cursorrules
When the user asks about invoice generator, use invoice-generator-ai-mcp tools: generateinvoice, calculatetotals, validateinvoice, listtemplates.
archive-mode-map
Visual process map for ARCHIVE mode (Task Documentation).