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.
git clone --depth 1 https://github.com/ellmos-ai/build-your-users-mindWrote 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/ellmos-ai/build-your-users-mind/decide-like-me)<a href="https://agentmods.dev/commands/ellmos-ai/build-your-users-mind/decide-like-me"><img src="https://agentmods.dev/badge/commands/ellmos-ai/build-your-users-mind/decide-like-me/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/ellmos-ai/build-your-users-mind/decide-like-me"><img src="https://agentmods.dev/badge/commands/ellmos-ai/build-your-users-mind/decide-like-me.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 | $0.00000 | $0.00286 |
| Opus 5 | $0.00000 | $0.00143 |
| Sonnet 5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
decide-like-me 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.
What it actually says
decide-like-me — Decide this one thing the way would (a fork, no side effect)
Run the preference model in decision-support mode. Read the avatar files in <AVATAR_DIR> and
follow START.md. The result is a fallible hypothesis, not a fact about the user or an authority grant.
Decision to make: $ARGUMENTS
Steps (0→2, then return a decision)
- (0) Project
DECISIONS.mdrelevant? → if so, it wins. - (1) Evidenced rule in
WHAT-<USER>-SAID.md? → decide accordingly. - (2) Otherwise prediction + confidence from
WHAT-WOULD-<USER>-SAY.md.
Output
- Decision: the concrete choice would make.
- Rationale: what it rests on (evidence/pattern).
- Confidence: 🟢/🟡/🔴.
- On 🔴: do NOT decide — escalate (ask the user) and say so.
This command performs no side effect (no push/write/delete) — it only returns the fork, which makes
it usable as a workflow component: the caller (e.g. be-my-avatar or avatar-orchestrator)
executes the decision.
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.
- 10d ago First seen · 22 lines · 0 tokens per session scan A 4b89c1e27cef
decide-like-me is a command published in the GitHub repository ellmos-ai/build-your-users-mind (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 286 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.
Other commands, from other repositories
aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
inbox
Check and respond to inter-agent messages.
caveman-compress
Compress a markdown/text file into caveman format to save tokens.
inventory
Track wiki-adjacent things the user cares about: items, Ideas, ingest candidates, entities, corpora, open questions, tasks, and other durable inventory records.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
fire-todos
Capture, list, and manage todos during work sessions.