scan

scan is a command for Claude Code from tiny-cloud-ventures/amnesia. It costs 13 tokens per session (233 once invoked), scanned A, original, MIT.

A command that checks Claude Code's saved memory for contradictions, outdated facts, duplicates, and memories filed in the wrong place.

In plain words
What is it for?
Run it when you want an audit of memory quality. It reports the problems it finds and points to the command for reviewing them one at a time.
Why use it?
It turns a large memory store into a plain-language summary, so you do not have to inspect every saved entry yourself.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the amnesia plugin — 2 commands shipped together

Good fit Run it when you want an audit of memory quality.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add tiny-cloud-ventures/amnesia
Claude Code
/plugin install amnesia

Made for: Claude Code.

Or install amnesia, the plugin that ships this one along with the rest of its 2 commands.

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 scan

README.md
[![agentmods](https://agentmods.dev/badge/commands/tiny-cloud-ventures/amnesia/scan.svg)](https://agentmods.dev/commands/tiny-cloud-ventures/amnesia/scan)
Your own site
<a href="https://agentmods.dev/commands/tiny-cloud-ventures/amnesia/scan"><img src="https://agentmods.dev/badge/commands/tiny-cloud-ventures/amnesia/scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 233 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.00233
Opus 5 $0.00006 $0.00117
Sonnet 5 $0.00003 $0.00047
Haiku 4.5 $0.00001 $0.00023

Measured 6d ago against content hash 7b66e3162fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scan 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 6d 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.

commands/scan.md · 12 lines

What it actually says

Run the amnesia memory audit and tell the user what it found, in plain language.

  1. Run python3 "${CLAUDE_PLUGIN_ROOT}/amnesia.py" analyze with a 10-minute Bash timeout — it feeds the whole memory store through the user's own claude CLI, so it takes a few minutes. If it fails because the claude CLI is missing from PATH, say so and stop.
  2. Read ~/.claude/amnesia/analysis.json.
  3. Summarize the findings as short human sentences — "Two memories disagree about which port X runs on", not filenames or JSON. Lead with the count: contradictions first, then stale facts, then duplicates and misfiled memories. If there is nothing to report, say the memory store looks clean and stop.
  4. Close with: run /amnesia:open to review and fix them one at a time (fixes are one click and reversible — everything goes to trash, never deleted).
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. 6d ago First seen · 12 lines · 13 tokens per session scan A 7b66e3162fc7

Subscribe to this mod's changes

scan is a command published in the GitHub repository tiny-cloud-ventures/amnesia (7 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 233 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 2026-08-31.