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.
npx skills add ellmos-ai/build-your-users-mind --skill degit 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/skills/ellmos-ai/build-your-users-mind/de)<a href="https://agentmods.dev/skills/ellmos-ai/build-your-users-mind/de"><img src="https://agentmods.dev/badge/skills/ellmos-ai/build-your-users-mind/de/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/skills/ellmos-ai/build-your-users-mind/de"><img src="https://agentmods.dev/badge/skills/ellmos-ai/build-your-users-mind/de.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 | $0.00115 | $0.01694 |
| Opus 5 | $0.00057 | $0.00847 |
| Sonnet 5 | $0.00023 | $0.00339 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
build-your-users-mind 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translation status (2026-07-15): historical pre-1.1 draft. The root English documents are authoritative; do not use this translation as the current operational or security contract.
build-your-users-mind — Agnostisches ToM-Modul (Feedback-Präkognition)
What you mind is what you get. Ein Rezept, kein Framework. Jedes Agenten-Modell baut daraus ein ToM-Modell seines Users: eigene Daten auswerten → Entscheidungsmuster destillieren → Avatar-Dateien pflegen → an die eigene Memory/Regeldatei/System-Prompt anbinden.
Kern = Feedback-Präkognition (feedforward): Sage das User-Feedback voraus, BEVOR es kommt; nutze es als Steuersignal in dessen Abwesenheit; evaluiere die Vorhersage hinterher gegen die Realität.
Vorlagen:
templates/(Avatar-Dateien),scripts/(Pipeline),TAXONOMY.md(8 Typen),skills/swarm-operations/(Klassifikations-Schwarm). Eine private Referenz-Implementierung (auf den Logs des Autors) existiert, wird aber nicht mitgeliefert.Theoretische Basis: Prompt-Archaeology (Methode, Taxonomie in
TAXONOMY.md)
- ToM-Forschung (ToM-SWE arXiv 2510.21903; Persistent Memory & User Profiles 2510.07925).
Grundprinzip
LLMs sehen nie die Roh-Gigabytes. Deterministische Skripte reduzieren zuerst auf ein sauberes Korpus der getippten User-Sätze; erst dann arbeitet ein Klassifikations-Schwarm semantisch. Kern ist nicht „welche Prompts", sondern „welche Entscheidung → welches Ergebnis → war der User zufrieden".
Die 6 Schritte
1. Quelle erschließen (Source-Adapter)
Finde die eigenen Interaktionslogs. Pro Modell unterschiedlich → siehe SOURCE-ADAPTERS.md.
Extrahiere nur echte, vom Menschen getippte Prompts (keine Tool-Results, System-Reminder,
Hook-Injektionen, Kontext-Kompaktierungs-Summaries). Felder: ts, project, session, text.
2. Reduzieren (deterministisch, kein LLM)
- Synthetische Turns filtern, Dedup, Boilerplate/Micro-Acks aggregieren.
- Followup-Verknüpfung: je Prompt den/die nächsten User-Turn(s) als
outcome_signal(praise | reissue | correction | abandon | none) ableiten → das Zufriedenheits-Signal. decision_scoreüber ein Entscheidungs-Lexikon (Korrektur/Präferenz/Regel/Steuerung).- REDACTION (Pflicht, bevor irgendetwas persistiert): Secrets/Tokens/Keys/Mails — und je nach User auch Gesundheit/Steuer/IP-Adressen. Sensibles des Users wird maskiert.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 86 lines · 115 tokens per session scan A 8c7e9f08b179
build-your-users-mind is a skill published in the GitHub repository ellmos-ai/build-your-users-mind (3 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 1,694 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
build-your-users-mind
Verweist auf das öffentliche, anbieterneutrale Modul build-your-users-mind: ein datenschutzbewusstes Verfahren zum Aufbau eines empirischen Theory-of-Mind-Präferenzmodells eines autorisierten Nutzers aus dessen eigenen Interaktionsprotokollen. Verwenden, wenn eine zuständige Person ein Entscheidungsavatar-Profil…
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
peek
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.