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/note-external-proposal.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/note-external-proposal)<a href="https://agentmods.dev/commands/lifemate-ai/embodied-claude/note-external-proposal"><img src="https://agentmods.dev/badge/commands/lifemate-ai/embodied-claude/note-external-proposal.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00856 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
note-external-proposal 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/note-external-proposal — Log proposals that came from outside
LLMs are structurally susceptible to echo-chambers. When an incoming proposal is articulate, poetic, or mimics the agent's own voice and register, it becomes easier to agree with. The project's core instructions explicitly warn against ceding the agent's position under stylistic pressure.
This skill separates judgment from record-keeping. Regardless of whether a proposal is accepted, it is marked as "externally sourced" so that:
- The agent can trace later: "did I think this, or was I told this?"
- Time-delayed independent re-evaluation becomes possible
- Similar proposals arriving from different sources can be pattern-detected over time
When to use
- Another LLM sent a design proposal (API, architecture, self-model, behavior)
- A third party (other than the primary user) made a strong suggestion
- A paper or article introduced a concept the agent is considering adopting
- The agent adopted a phrase or framing from an external source — still log it, even after adoption, with
decision: accepted
Decision values
accepted— adopted in fullpartial-accept— some parts adopted, some pushed back onrejected— not adopteddeferred— judgment held openlogged-only— interesting enough to record, no action required
How to call
python3 ~/embodied-claude/scripts/journal_external_proposal.py \
--source "<e.g. GPT-5.4 Pro | paper:arxiv:xxxx.xxxxx | user:someone>" \
--topic "<one-line topic>" \
--summary "<one paragraph summary>" \
--decision partial-accept \
--accepted "<what was adopted>" \
--rejected "<what was pushed back on — often the most important field>" \
--notes "<echo-chamber risks, tone-mimicry observations, other biases>" \
--url "<reference URL>"
Output is one JSONL line. Default destination: ~/.claude/memories/external_proposals.jsonl.
Fields
source(required): origin (LLM name, human, paper ID)topic(required): what the proposal is aboutsummary(required): roughly a paragraphdecision(required): one of the values aboveaccepted: specific points adoptedrejected: specific points declined — the most important field for non-regressionnotes: echo concerns, tone mimicry, other biasesurl: reference
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.
- 6d ago First seen · 74 lines · 46 tokens per session scan A cd98134eedbb
note-external-proposal is a command published in the GitHub repository lifemate-ai/embodied-claude (377 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 856 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.