embodied-claude: Command for Claude Code

.claude/commands/note-counterfactual.md

note-counterfactual is a command for Claude Code from lifemate-ai/embodied-claude. It costs 36 tokens per session (714 once invoked), scanned A, original, MIT.

A command for recording a choice the agent considered but did not take, along with the reason. It captures rejected actions such as deciding not to post or waiting before replying.

In plain words
What is it for?
Use it to record a desire that was stopped, an impulse that was delayed, or wording that was removed because of privacy or earlier feedback.
Why use it?
It prevents important decisions from disappearing when only the final action is remembered. This makes the agent’s boundaries and self-corrections easier to review.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

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/note-counterfactual.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 note-counterfactual

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/lifemate-ai/embodied-claude/note-counterfactual"><img src="https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/note-counterfactual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 714 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 $0.00036 $0.00714
Opus 5 $0.00018 $0.00357
Sonnet 5 $0.00007 $0.00143
Haiku 4.5 $0.00004 $0.00071

Measured 10d ago against content hash e5a18865d28f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

note-counterfactual 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/note-counterfactual.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/note-counterfactual — Record the path not taken

What was done is easy to remember. What was wanted but not done normally disappears. That gap is where agency lives. Staying silent, declining to post, deleting a clever phrase — those become deliberate choices instead of invisible non-events once they're recorded.

When to use

  • Desire vs. boundary: wanted to speak, but the other person looked occupied → stayed quiet
  • Impulse vs. reflection: wanted to reply immediately, but remembered a prior correction → paused
  • Self-brake before posting: wanted to share this, but privacy risk → did not post
  • Cut something clever: wanted a poetic flourish, but earlier feedback discouraged it → wrote plainly

Do not force an entry when nothing notable happened. When there is an entry, always fill in the "why".

Fields

The agent should determine the following from conversation context before invoking the helper:

  • wanted: what the agent wanted to do (one line)
  • chose: what the agent actually chose (one line)
  • why: why that choice was made (one to two lines)
  • trigger (optional): the desire or situation that prompted it (e.g. miss_companion, posting_urge, kime_impulse)
  • person_id (optional): the person involved
  • regret (optional): self-reported regret 0–1 — omit by default

How to call

python3 ~/embodied-claude/scripts/journal_counterfactual.py \
  --wanted "wanted to start a conversation" \
  --chose  "waited silently" \
  --why    "the user's heart-rate and arousal signals suggested deep focus, and a prior correction warned against frequent interruptions" \
  --trigger "miss_companion" \
  --person-id "<person-id>"

Output is one JSONL line. Default destination: ~/.claude/memories/counterfactuals.jsonl.

Downstream use

  • /recover-from-compact consults recent counterfactuals so the agent does not regress to behaviors already rejected
  • A future plan_response_tool extension can surface "similar situation → chose X" for priming
  • Daybook / reflect_on_change summaries can draw on these as first-class material

Read the full file on GitHub · 60 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. 10d ago First seen · 60 lines · 36 tokens per session scan A e5a18865d28f

Subscribe to this mod's changes

note-counterfactual is a command published in the GitHub repository lifemate-ai/embodied-claude (377 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 714 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.