turritopsis-personal-ai-assistant

turritopsis-personal-ai-assistant is a skill for Codex from anhe2021212-spec/Turritopsis. It costs 83 tokens per session (269 once invoked), scanned A, original, MIT.

A design guide for personal AI assistants that defines their role, permissions, relationships with people, memory, communication channels, and actions.

In plain words
What is it for?
Use it to design, review, or repair how a private assistant behaves, remembers preferences, takes actions, and keeps a clear relationship with its human owner.
Why use it?
It helps prevent an assistant from treating familiarity or confidence as permission to act. It also makes consent, explanations, and failures explicit.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to design, review, or repair how a private assistant behaves, remembers preferences, takes actions, and keeps a clear relationship with its human owner.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant
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.

Any agent
npx skills add anhe2021212-spec/Turritopsis --skill turritopsis-personal-ai-assistant
Clone the repo
git clone --depth 1 https://github.com/anhe2021212-spec/Turritopsis

Made for: Codex.

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 turritopsis-personal-ai-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant/github.svg)](https://agentmods.dev/skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant)
Your own site
<a href="https://agentmods.dev/skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant"><img src="https://agentmods.dev/badge/skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant/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 turritopsis-personal-ai-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant"><img src="https://agentmods.dev/badge/skills/anhe2021212-spec/turritopsis/turritopsis-personal-ai-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 269 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 $0.00083 $0.00269
Opus 5 $0.00042 $0.00134
Sonnet 5 $0.00017 $0.00054
Haiku 4.5 $0.00008 $0.00027

Measured 12d ago against content hash b6314386dce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

turritopsis-personal-ai-assistant 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.

skills/turritopsis-personal-ai-assistant/SKILL.md · 18 lines

What it actually says

Turritopsis Personal AI Assistant

Map the assistant as a relationship with explicit authority, not as a persona plus tools.

  1. Use $turritopsis-onboarding for local scan and validated application.
  2. Read stage-suite.md.
  3. Define the assistant's role, non-role, human owner, channels, and action surface before describing personality.
  4. Separate human consent and direction, remembered preferences, runtime evidence, model inference, and external-service state.
  5. Give every proactive or consequential action an explicit authority level, confirmation rule, visible result, and failure behavior.
  6. Preserve warmth and continuity without treating intimacy, repetition, or confidence as permission.
  7. Keep user-facing explanations distinct from private internal scheduling, ranking, or safety inputs.
  8. Use fixture.json only as a fictional quality example.
Files

What ships with it

3 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.

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 · 18 lines · 83 tokens per session scan A b6314386dce3

Subscribe to this mod's changes

turritopsis-personal-ai-assistant is a skill published in the GitHub repository anhe2021212-spec/Turritopsis (13 stars, last pushed 17d ago), licensed MIT. It adds 83 tokens to every session and 269 once invoked, about $0.0004 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.