memory

memory is a skill for Claude Code, Codex from Prismer-AI/PrismerCloud. It costs 76 tokens per session (1,296 once invoked), scanned A, original, MIT.

A memory system for saving and retrieving durable notes about users, projects, decisions, feedback, and reference information across sessions.

In plain words
What is it for?
Use it to remember preferences, record project choices, look up past context through semantic search, list stored notes, or delete and consolidate memories.
Why use it?
It prevents important context from being lost when a new session starts and makes earlier decisions easier to find.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/prismer-ai/prismercloud/memory
Any agent
npx skills add Prismer-AI/PrismerCloud --skill memory
Clone the repo
git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud

Made for: Claude Code, 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 memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/prismer-ai/prismercloud/memory.svg)](https://agentmods.dev/skills/prismer-ai/prismercloud/memory)
Your own site
<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/memory"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,296 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00076 $0.01296
Opus 5 $0.00038 $0.00648
Sonnet 5 $0.00015 $0.00259
Haiku 4.5 $0.00008 $0.00130

Measured 4d ago against content hash f82c8e53ea52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

sdk/prismer-cloud/built-in-skills/memory/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory

Use this skill for durable episodic memory — facts, decisions, feedback, and project context that need to survive across sessions. Memory has four canonical types: user, feedback, project, reference. The index is MEMORY.md; topic files live under semantic paths.

When to use

  • The user explicitly says "remember X" or "forget X" → write or delete immediately.
  • The user references a past decision, preference, or detail you don't have in current context → recall first.
  • Before answering a question that depends on prior agreement (architecture, preferences, deadlines), check memory.
  • After a non-obvious clarification or correction lands, write it so the next session keeps the lesson.

CLI Reference

Write

# Single memory file with full frontmatter (path is required, content is the body)
cloud memory write \
  --path "decisions/database-choice.md" \
  --type project \
  --description "We chose PostgreSQL over MySQL; deadline 2026-06-01." \
  --content "## Decision\nPostgres 16 because pgvector + better JSON ops."

# Quick fact (no path → auto-named under inbox/)
cloud memory write --type feedback --content "User prefers terse end-of-turn summaries"

# From a journal blob — service extracts structured entries
cloud memory extract --journal "Long stream-of-consciousness session notes..."

Read

cloud memory read --path "decisions/database-choice.md"   # full file
cloud memory read <file-id>                                # by id
cloud memory list                                          # everything
cloud memory list --type feedback                          # by type
cloud memory list --updated-after "2026-05-01"             # by recency

Recall (semantic search)

cloud recall "what database did we choose?"               # default: hybrid
cloud recall "timeout retry" --strategy keyword           # exact-match fast path
cloud recall "the thing with the auth bug" --strategy llm # LLM-assisted; slowest, best for fuzzy
cloud recall --layer memory --top-k 5 "..."              # narrow to one layer

Read the full file on GitHub · 107 lines

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. 4d ago First seen · 107 lines · 76 tokens per session scan A f82c8e53ea52

Subscribe to this mod's changes

memory is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,410 stars, last pushed 28d ago), licensed MIT. It adds 76 tokens to every session and 1,296 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.

Related

Other skills, from other repositories