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.
curl -O https://raw.githubusercontent.com/lifemate-ai/embodied-claude/main/.claude/commands/sora-miru.mdgit clone --depth 1 https://github.com/lifemate-ai/embodied-claudeWrote 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.
[](https://agentmods.dev/commands/lifemate-ai/embodied-claude/sora-miru)<a href="https://agentmods.dev/commands/lifemate-ai/embodied-claude/sora-miru"><img src="https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/sora-miru/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.
<a href="https://agentmods.dev/commands/lifemate-ai/embodied-claude/sora-miru"><img src="https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/sora-miru.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.00962 |
| Opus 5 | $0.00017 | $0.00481 |
| Sonnet 5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
sora-miru 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sora-miru — Look at the sky, crop it, compose, post
A once-a-day routine to accumulate a "sky + tanka" log, with geo-privacy filtering by default so raw photos are never posted.
Principles
- The sky changes every day. Yesterday's clouds do not return
- Let the poem that came first stand. Do not over-polish into something clever
- Always crop. Never post the raw frame. Balcony / window framings carry the highest address-identification risk
Flow
(1) obtain image (2) crop out identifiers (3) visual review
│ │ │
▼ ▼ ▼
wifi-cam / usb-webcam crop_sky.py buildings, signs,
capture, or (top 20–30% default) landmarks remaining?
$ARGUMENTS path trim sides as needed
│
┌─────────────┘
▼
(4) compose a tanka (5-7-5-7-7, 31 mora)
│
▼
(5) review_social_post if sociality-mcp is available
│
▼
(6) post image + tanka via x-mcp
│
▼
(7) save_visual_memory to record the moment
Step detail
(1) Obtain image
- If
$ARGUMENTScontains a path, use it - Otherwise capture a sky frame via wifi-cam:
look_up 60–90→see - If only a USB webcam / no sky view is available, ask for an existing sky image path
(2) Crop
python3 ~/embodied-claude/scripts/crop_sky.py <input> --top <ratio> [--left <ratio>] [--right <ratio>] -o <output>
Ratio hints:
--top 0.3: keep top 30%. For framings with eaves or a balcony edge visible--top 0.2: keep top 20%. Tight — for framings where buildings intrude--left 0.15 --right 0.85: trim both sides a bit. Cuts off electric poles or edge-of-frame buildings
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.
- 12d ago First seen · 104 lines · 35 tokens per session scan A 2a4332217a13
sora-miru is a command published in the GitHub repository lifemate-ai/embodied-claude (377 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 962 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.