A command for cleaning up Engram, a project memory system that stores linked notes. It reviews related notes, records the current state, merges repeated information, and marks reviewed notes.

Use it to review groups of related notes, record settled decisions, connect replacements and answers, and identify notes that still need attention.

It helps reduce conflicting, duplicated, or outdated project notes so the stored project history is easier to use.

sleep — Command for Claude Code by techtheist/engram

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.

Clone the repo

git clone --depth 1 https://github.com/techtheist/engram

Made for: Claude Code.

Or install engram, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 1 MCP server.

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/commands/techtheist/engram/sleep/github.svg)](https://agentmods.dev/commands/techtheist/engram/sleep)

Your own site

<a href="https://agentmods.dev/commands/techtheist/engram/sleep"><img src="https://agentmods.dev/badge/commands/techtheist/engram/sleep/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/commands/techtheist/engram/sleep"><img src="https://agentmods.dev/badge/commands/techtheist/engram/sleep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 260 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	$0.00043	$0.00260
Opus 5.5	$0.00017	$0.00104
Sonnet 5.5	$0.00009	$0.00052
Haiku 4.5	$0.00004	$0.00026

Measured 5d ago against content hash 1af6725d9334, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sleep 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.

claude-plugin/commands/sleep.md · 12 lines

What it actually says

The user wants an Engram sleep sweep.

Invoke the engram-sleep skill and follow it end to end: settle conflicts first (list_nodes view: "conflicts"), then delegate each subject to a fresh subagent with the skill's brief, read subjects with list_nodes view: "review" (or around for a named subject), tie islands back in last (view: "islands"), write the state-of note for settled history, merge restatements, link supersessions and answers, judge listed suspects, mark every note left standing reviewed, and finish with the audible report, including how to undo the session in the pane.

If the engram MCP tools are not available in this session, stop and run /engram:setup first.

$ARGUMENTS names a subject (a tag, an anchor or note id, or a phrase to search) when present; otherwise work the review queue from the top, one subject per subagent, up to three subjects.

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 · 12 lines · 0 tokens per session scan A 1af6725d9334

Subscribe to this mod's changes

sleep is a command published in the GitHub repository techtheist/engram (36 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 260 once invoked, about $0.0002 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 2026-11-01.

Memory Management Memory and context ai-memory ai-memory-system claude-code-plugin cli-tool

sleep next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sleeptechtheist/engram	Command	36	6d ago	MIT	A	43	Claude Code
savelinxule/memex-plugin	Command	7	yesterday	MIT	A	13	Claude Code
statuslinxule/memex-plugin	Command	7	yesterday	MIT	A	15	Claude Code
tl-exportAgusLoza2021/Thoughtline	Command	4	20d ago	MIT	A	15	Claude Code
tl-recentAgusLoza2021/Thoughtline	Command	4	20d ago	MIT	A	12	Claude Code
tl-searchAgusLoza2021/Thoughtline	Command	4	20d ago	MIT	A	12	Claude Code
tl-statsAgusLoza2021/Thoughtline	Command	4	20d ago	MIT	A	13	Claude Code