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 agentmods add skills/danielrosehill/claude-user-memory-plugin/recall-user-memorynpx skills add danielrosehill/Claude-User-Memory-Plugin --skill recall-user-memorygit clone --depth 1 https://github.com/danielrosehill/Claude-User-Memory-PluginWrote 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/danielrosehill/claude-user-memory-plugin/recall-user-memory)<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>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 | $0.00107 | $0.00646 |
| Opus 5 | $0.00053 | $0.00323 |
| Sonnet 5 | $0.00021 | $0.00129 |
| Haiku 4.5 | $0.00011 | $0.00065 |
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.
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
- Load the config — read
.claude/memory-config.mdin 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'stemplates/memory-config.example.md). - Pick the context — apply the deduction rule from
CONTEXT.md(default personal; switch to work on explicit override, work cwd, or clearly-business conversation). - 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".
- The context's scope parameters from
- 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-factto overwrite). - 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).
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.
- 5d ago First seen · 33 lines · 107 tokens per session scan A 73d6a11456e6
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.
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.
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.…
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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.
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…