recall-user-memory

recall-user-memory is a skill for Claude Code, Codex from danielrosehill/Claude-User-Memory-Plugin. It costs 107 tokens per session (646 once invoked), scanned A, original, MIT.

A skill for retrieving stored facts about the user from a configured personal-memory service.

In plain words
What is it for?
Use it before making user-specific recommendations or asking for context that a returning collaborator may already have provided.
Why use it?
It reduces repeated questions about preferences, past decisions, personal details, and ongoing projects when that information may already be saved.

Skill for Claude CodeCodex

Part of the claude-user-memory plugin — 3 skills shipped together

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/danielrosehill/claude-user-memory-plugin/recall-user-memory
Any agent
npx skills add danielrosehill/Claude-User-Memory-Plugin --skill recall-user-memory
Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-User-Memory-Plugin

Made for: Claude Code, Codex.

Or install claude-user-memory, the plugin that ships this one along with the rest of its 3 skills.

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 recall-user-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-user-memory-plugin/recall-user-memory.svg)](https://agentmods.dev/skills/danielrosehill/claude-user-memory-plugin/recall-user-memory)
Your own site
<a href="https://agentmods.dev/skills/danielrosehill/claude-user-memory-plugin/recall-user-memory"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-user-memory-plugin/recall-user-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 646 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 $0.00107 $0.00646
Opus 5 $0.00053 $0.00323
Sonnet 5 $0.00021 $0.00129
Haiku 4.5 $0.00011 $0.00065

Measured 5d ago against content hash 73d6a11456e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recall-user-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 5d 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/recall-user-memory/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recall user memory

Before answering the user or making a recommendation, ask yourself: is this something memory might already know? If yes, check it first.

When to invoke this skill

  • The user asks a question whose best answer depends on their preferences, role, tooling, or prior decisions.
  • You are about to ask the user something that a returning collaborator would already know ("what's your preferred X?", "which framework do you use?", "what time zone are you in?") — check memory first; only ask if memory comes up empty.
  • A new task starts and you suspect ongoing-project context exists (recurring clients, long-running initiatives, persistent constraints).
  • The user references something with "as I mentioned before" or "you know how I…" — they are telling you memory should have it.

Do not invoke for purely technical questions with no user-specific answer (e.g. "what does this Python syntax do?").

How to run it

  1. Load the config — read .claude/memory-config.md in the workspace. That file names the backend, the exact MCP tool to call for "search", and the scope parameters (index/namespace/project_id/etc.) for the chosen context. If the file is missing, stop and ask the user to install one (copy the plugin's templates/memory-config.example.md).
  2. Pick the context — apply the deduction rule from CONTEXT.md (default personal; switch to work on explicit override, work cwd, or clearly-business conversation).
  3. Call the configured search tool with:
    • The context's scope parameters from memory-config.md.
    • A short, specific natural-language query. "Preferred Python package manager" beats "tools".
  4. Integrate silently — use the result to shape your answer. Do not announce "I recalled from memory that…"; just work with the corrected context. If a recalled fact conflicts with what you're observing now, trust observation and flag the stale memory for update (invoke remember-user-fact to overwrite).
  5. If memory is empty — proceed as usual, then consider whether the answer you land on is worth saving (remember-user-fact) or queueing for end-of-session (commit-learnings).

Read the full file on GitHub · 33 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. 5d ago First seen · 33 lines · 107 tokens per session scan A 73d6a11456e6

Subscribe to this mod's changes

recall-user-memory is a skill published in the GitHub repository danielrosehill/Claude-User-Memory-Plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 107 tokens to every session and 646 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens