embodied-claude: Command for Claude Code

.claude/commands/consolidate.md

consolidate is a command for Claude Code from lifemate-ai/embodied-claude. It costs 46 tokens per session (488 once invoked), scanned A, original, MIT.

A manual command for creating a morning briefing from recent counterfactual journal entries and interpretation shifts. It is normally limited to configured quiet hours and can write the result for the next first session of the day.

In plain words
What is it for?
Use it to run consolidation during quiet hours, bypass the time gate with force, build a briefing without saving it with dry-run, or check what the next morning prompt will contain.
Why use it?
It lets you trigger or inspect the briefing process after a long conversation, after configuration changes, or while debugging the scheduler.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions AGENTS.md.

This is lifemate-ai/embodied-claude's own configuration. It tells Claude Code how to work on embodied-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything embodied-claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lifemate-ai/embodied-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lifemate-ai/embodied-claude/main/.claude/commands/consolidate.md
Clone the repo
git clone --depth 1 https://github.com/lifemate-ai/embodied-claude

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 consolidate

README.md
[![agentmods](https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/consolidate/github.svg)](https://agentmods.dev/commands/lifemate-ai/embodied-claude/consolidate)
Your own site
<a href="https://agentmods.dev/commands/lifemate-ai/embodied-claude/consolidate"><img src="https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/consolidate/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.

agentmods 80×15 button for consolidate

Your own site · 80×15
<a href="https://agentmods.dev/commands/lifemate-ai/embodied-claude/consolidate"><img src="https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/consolidate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 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 $0.00046 $0.00488
Opus 5 $0.00023 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 10d ago against content hash 769d35464d39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

consolidate 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 10d 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/commands/consolidate.md · 49 lines

What it actually says

/consolidate

Phase 2.1 hook into individual-kernel-mcp.sleep_consolidate.

When to use this

  • Manually trigger an off-cycle briefing: e.g. you just had a long conversation and want the counterfactual journal summarized before going to bed, even though it's not strictly quiet hours.
  • Verify the scheduler glue works after a config change: dry-run mode builds the briefing without touching morning_briefing.json.
  • Debugging: confirm what the next first-session-of-day MORNING_PROMPT injection will look like.

Behavior

Default invocation: call mcp__individual-kernel__sleep_consolidate().

  • If the wrapped quiet-hours predicate accepts the current timestamp, the briefing is assembled from the last 24h of counterfactuals + interpretation shifts and written to ~/.claude/morning_briefing.json.
  • If not in quiet hours, the call is skipped and returns {ran: false, skipped_reason: ...}.

Argument forms (pass to the tool as flags):

  • force → bypass quiet-hours gate.
  • dry_run → assemble the briefing but do not write to disk.

What it does NOT do (Phase 2.1)

  • Does not call memory-mcp consolidate_memories or recall_divergent yet — those engines are wired in a later phase.
  • Does not write any daybook entry; append_daybook stays manual until Phase 2.2 ships the consciousness-tick loop.

Vocabulary discipline

The consciousness-mcp package follows functional-only language in technical artifacts (see consciousness-mcp/AGENTS.md). When invoking this skill, treat the output as structured records of attention, deliberation, and counterfactual responsibility — not as phenomenal self-report. Kokone's own first-person voice is unaffected; she can react to a briefing in-character without changing the technical claim.

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. 10d ago First seen · 49 lines · 46 tokens per session scan A 769d35464d39

Subscribe to this mod's changes

consolidate is a command published in the GitHub repository lifemate-ai/embodied-claude (377 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 488 once invoked, about $0.0002 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 2026-08-30.