turritopsis-agent-memory

turritopsis-agent-memory is a skill for Codex from anhe2021212-spec/Turritopsis. It costs 74 tokens per session (290 once invoked), scanned A, original, MIT.

A design guide for systems that store knowledge across sessions or agents, including evidence, corrections, retention, and search indexes.

In plain words
What is it for?
Use it to design or review shared project memory, long-term recall, evidence ingestion, retrieval, corrections, deletion, and retention rules.
Why use it?
It helps separate verified information from summaries, old events, and generated search data. This reduces the risk of remembering guesses as facts.

Skill for Codex

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

Good fit Use it to design or review shared project memory, long-term recall, evidence ingestion, retrieval, corrections, deletion, and retention rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anhe2021212-spec/turritopsis/turritopsis-agent-memory
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-agent-memory
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-agent-memory

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/anhe2021212-spec/turritopsis/turritopsis-agent-memory"><img src="https://agentmods.dev/badge/skills/anhe2021212-spec/turritopsis/turritopsis-agent-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 290 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 $0.00074 $0.00290
Opus 5 $0.00037 $0.00145
Sonnet 5 $0.00015 $0.00058
Haiku 4.5 $0.00007 $0.00029

Measured 12d ago against content hash 34ff5d336138, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

turritopsis-agent-memory 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-agent-memory/SKILL.md · 20 lines

What it actually says

Turritopsis Agent Memory

Design memory as governed knowledge, not as a chat archive.

  1. Use $turritopsis-onboarding for the local scan and validated skeleton workflow.
  2. Read stage-suite.md before classifying this project.
  3. Select only the responsibilities the implementation actually has. Rename Currents for the project; never copy the fixture mechanically.
  4. Give raw evidence, accepted knowledge, episodic history, summaries, and retrieval indexes separate Authority.
  5. Treat embeddings, caches, and search indexes as rebuildable generated data unless the project explicitly makes them canonical.
  6. Record correction, deletion, retention, and provenance behavior as first-class contracts.
  7. Leave unsupported beliefs unknown. Do not promote fluent inference into remembered fact.
  8. Use fixture.json only as a quality example.

When filling bodies, answer the retrieval question first, cite real evidence, and add update triggers for schema, ingestion, ranking, retention, and correction changes.

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 · 20 lines · 74 tokens per session scan A 34ff5d336138

Subscribe to this mod's changes

turritopsis-agent-memory is a skill published in the GitHub repository anhe2021212-spec/Turritopsis (13 stars, last pushed 17d ago), licensed MIT. It adds 74 tokens to every session and 290 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.