A storage format saves the original data captured during a synchronization, including metadata, one JSON file per entity, and optional binary files. The saved data can be read back for replay, debugging, and evaluation.

Use it to capture sync results, reconstruct entities, replay data, and store captures on a filesystem or cloud storage such as S3, Azure Blob, or Google Cloud Storage.

It preserves the exact input from a sync so problems can be investigated or tests can be repeated without contacting the original source again.

arf — Cursor rule for Cursor by airweave-ai: A storage format saves the original data captured during…

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.

agentmods

npx agentmods add rules/airweave-ai/airweave/arf

Clone the repo

git clone --depth 1 https://github.com/airweave-ai/airweave

Made for: Cursor.

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/rules/airweave-ai/airweave/arf.svg)](https://agentmods.dev/rules/airweave-ai/airweave/arf)

Your own site

<a href="https://agentmods.dev/rules/airweave-ai/airweave/arf"><img src="https://agentmods.dev/badge/rules/airweave-ai/airweave/arf.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 388 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.00388
Opus 5	$0.00000	$0.00194
Sonnet 5	$0.00000	$0.00078
Haiku 4.5	$0.00000	$0.00039

Measured 5d ago against content hash b450f1e5bd96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arf 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 5d 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.

.cursor/rules/arf.mdc · 32 lines

What it actually says

Airweave Raw Format (ARF)

Raw entity capture for replay, debugging, and evals.

Structure

raw/{sync_id}/
├── manifest.json          # Sync metadata
├── entities/{id}.json     # One file per entity
└── files/{id}_{name}      # Binary files (optional)

Key Files

StoragePaths: domains/storage/paths.py (path constants: arf_sync_path, arf_entity_path, safe_filename)
ArfService: domains/arf/service.py (write operations during sync, implements ArfServiceProtocol)
ArfReader: domains/arf/reader.py (entity reconstruction for replay, implements ArfReaderProtocol)
ArfReplaySource: domains/arf/replay_source.py (internal source for ARF replay)
Protocols: domains/arf/protocols.py (ArfServiceProtocol, ArfReaderProtocol)
Fakes: domains/arf/fakes/ (in-memory test doubles: FakeArfService, FakeArfReader)
StorageBackend protocol: domains/storage/protocols.py (injected into ArfService/ArfReader)
Storage adapters (FYI): adapters/storage/ (Filesystem, Azure Blob, AWS S3, GCP GCS)
Config: STORAGE_BACKEND (filesystem, azure, aws, gcp)

Usage

ArfService is injected into ArfHandler via EntityDispatcherBuilder. Capture happens during action dispatch (INSERT/UPDATE entities stored, DELETE entities removed). The ArfHandler lives in platform/sync/handlers/arf.py.

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.

5d ago First seen · 32 lines · 0 tokens per session scan A b450f1e5bd96

Subscribe to this mod's changes

arf is a cursor rule published in the GitHub repository airweave-ai/airweave (6,565 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 388 tokens. 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 2026-08-30.

Debugging LLM agent-infrastructure ai ai-agents search

arf

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Airweave Raw Format (ARF)

Structure

Key Files

Usage

What this file has done since we first saw it

Other cursor rules, from other repositories

development-phase

angular-20

dev-standard

cli-error-handling

prefer-direct-imports-over-module-mocks

control-plane-descriptors