rclone_checksum

rclone_checksum is a command for Claude Code from olorehq/olore. It costs 11 tokens per session (1,327 once invoked), scanned A, original, MIT.

A verification command that compares remote files with a checksum file, which is a list of expected file fingerprints. It reports mismatches without changing the files.

In plain words
What is it for?
Use it to validate backups or downloaded datasets against MD5, SHA1, or other checksum lists.
Why use it?
It provides a way to check whether stored files still match a trusted record. This can detect corruption, missing files, or unexpected changes.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/olorehq/olore/rclone_checksum
Clone the repo
git clone --depth 1 https://github.com/olorehq/olore

Made for: Claude Code.

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.

agentmods badge for rclone_checksum

README.md
[![agentmods](https://agentmods.dev/badge/commands/olorehq/olore/rclone_checksum.svg)](https://agentmods.dev/commands/olorehq/olore/rclone_checksum)
Your own site
<a href="https://agentmods.dev/commands/olorehq/olore/rclone_checksum"><img src="https://agentmods.dev/badge/commands/olorehq/olore/rclone_checksum.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,327 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.01327
Opus 5 $0.00005 $0.00664
Sonnet 5 $0.00002 $0.00265
Haiku 4.5 $0.00001 $0.00133

Measured 2d ago against content hash b053ef3cc91b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

rclone_checksum 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

vault/packages/rclone/1.74.3/contents/commands/rclone_checksum.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rclone checksum

Checks the files in the destination against a SUM file.

Synopsis

Checks that hashsums of destination files match the SUM file. It compares hashes (MD5, SHA1, etc) and logs a report of files which don't match. It doesn't alter the file system.

The sumfile is treated as the source and the dst:path is treated as the destination for the purposes of the output.

If you supply the --download flag, it will download the data from the remote and calculate the content hash on the fly. This can be useful for remotes that don't support hashes or if you really want to check all the data.

Note that hash values in the SUM file are treated as case insensitive.

If you supply the --one-way flag, it will only check that files in the source match the files in the destination, not the other way around. This means that extra files in the destination that are not in the source will not be detected.

The --differ, --missing-on-dst, --missing-on-src, --match and --error flags write paths, one per line, to the file name (or stdout if it is -) supplied. What they write is described in the help below. For example --differ will write all paths which are present on both the source and destination but different.

The --combined flag will write a file (or stdout) which contains all file paths with a symbol and then a space and then the path to tell you what happened to it. These are reminiscent of diff files.

  • = path means path was found in source and destination and was identical
  • - path means path was missing on the source, so only in the destination
  • + path means path was missing on the destination, so only in the source
  • * path means path was present in source and destination but different.
  • ! path means there was an error reading or hashing the source or dest.

The default number of parallel checks is 8. See the --checkers option for more information.

rclone checksum <hash> sumfile dst:path [flags]

Read the full file on GitHub · 119 lines

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.

  1. 2d ago First seen · 119 lines · 11 tokens per session scan A b053ef3cc91b

Subscribe to this mod's changes

rclone_checksum is a command published in the GitHub repository olorehq/olore (103 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,327 once invoked, about $0.0001 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 2026-09-03.