be-my-avatar

be-my-avatar is a command for Claude Code from ellmos-ai/build-your-users-mind. It costs 0 tokens per session (322 once invoked), scanned A, original, MIT.

An execution workflow that applies an authorized model of a user's preferences to a task. It can act only within existing permission and records what it did, its confidence, and later feedback.

In plain words
What is it for?
Use it after a preference model has made a decision to carry out approved local actions, log the assumption, and refine the model when the user responds.
Why use it?
It helps an agent handle routine, reversible actions while preventing assumptions from expanding its authority. High-impact, external, irreversible, or uncertain actions are escalated for confirmation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it after a preference model has made a decision to carry out approved local actions, log the assumption, and refine the model when the user responds.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ellmos-ai/build-your-users-mind/be-my-avatar
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/ellmos-ai/build-your-users-mind

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 be-my-avatar

README.md
[![agentmods](https://agentmods.dev/badge/commands/ellmos-ai/build-your-users-mind/be-my-avatar/github.svg)](https://agentmods.dev/commands/ellmos-ai/build-your-users-mind/be-my-avatar)
Your own site
<a href="https://agentmods.dev/commands/ellmos-ai/build-your-users-mind/be-my-avatar"><img src="https://agentmods.dev/badge/commands/ellmos-ai/build-your-users-mind/be-my-avatar/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 be-my-avatar

Your own site · 80×15
<a href="https://agentmods.dev/commands/ellmos-ai/build-your-users-mind/be-my-avatar"><img src="https://agentmods.dev/badge/commands/ellmos-ai/build-your-users-mind/be-my-avatar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 322 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 $0.00000 $0.00322
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 12d ago against content hash eac307be6b4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

be-my-avatar 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.

templates/commands/be-my-avatar.md · 24 lines

What it actually says

be-my-avatar — Apply an authorized preference hypothesis (full loop, with logging)

Run the preference model in action mode only inside authority the user already granted. Read the avatar files in <AVATAR_DIR> and follow START.md. The model is not an authority grant.

Task / situation: $ARGUMENTS

Steps (full 0→4 loop)

  1. Decide as in decide-like-me (0→2).
  2. Act — only if already authorized, reversible, local, and within pattern (≥🟡 confidence).
    • Irreversible / external / high-impact (push, upload, delete, mail, server, legal, medical, employment, financial, or safety-critical) or 🔴 → do NOT act; ask for confirmation.
  3. (3) Log: every action assumed on the user's behalf, with assumption + confidence, into WHAT-I-DID-…md and MY-ACTIONS.txt.
  4. (4) On later real feedback → record in WHAT-<USER>-SAID-ABOUT-…md and refine the rule in WHAT-<USER>-SAID.md.

Output

  • What was done (or why escalated), confidence, and a pointer to the log entry.

Golden rule: a pattern never expands authority. When in doubt, prefer asking over overreaching. As a workflow component this is the executing stage after decide-like-me.

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. 12d ago First seen · 24 lines · 0 tokens per session scan A eac307be6b4d

Subscribe to this mod's changes

be-my-avatar is a command published in the GitHub repository ellmos-ai/build-your-users-mind (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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 2026-08-31.