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/threat-vector-security/guardian-agent/preferences-memorynpx skills add Threat-Vector-Security/guardian-agent --skill preferences-memorygit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/preferences-memory)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/preferences-memory"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/preferences-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 5.1 | $0.00000 | $0.00348 |
| Opus 5 | $0.00000 | $0.00174 |
| Sonnet 5 | $0.00000 | $0.00070 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
preferences-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 6d 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.
What it actually says
Preferences Memory
Use memory tools only when the user explicitly wants a stable fact or preference remembered beyond the current conversation.
Workflow
- Confirm the thing is worth remembering.
- stable preference
- profile detail
- standing instruction
- recurring project context
- Check for an existing related memory first with
memory_searchormemory_recall. - Save a concise normalized memory with
memory_save. - Tell the user what was remembered in plain language.
Recurring Learnings
- If the user explicitly wants a lesson from this task retained for future conversations, normalize it into a short stable rule or project fact before saving it.
- Prefer one durable memory over a long incident log.
- Save only the part that will still matter later.
Do Not Turn This Into
- ad-hoc
.learnings/files - automatic hook installation
- autonomous self-improvement loops
- silent edits to
AGENTS.md,CLAUDE.md, or.github/copilot-instructions.md
Do Save
- preferred writing style or output format
- stable names, roles, or relationships the user wants reused
- recurring workflow preferences
- durable project context the user explicitly wants retained
Do Not Save
- one-off operational notes
- temporary status output
- approval bookkeeping
- transient paths, errors, or command results unless the user specifically asks to remember them
Gotchas
- Do not save memories implicitly from ordinary conversation; the user needs to want persistence.
- Do not store volatile logs, diagnostics, or ephemeral paths as durable memory.
- Do not turn memory into self-modifying prompts, local hook setup, or hidden configuration drift.
What ships with it
1 file 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.
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.
- 6d ago First seen · 48 lines · 0 tokens per session scan A 172799d87270
preferences-memory is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (11 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 348 tokens. 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.
Other skills, from other repositories
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
para-memory-files
File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns.…
agentlas-one
Use when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.
memory-ticketing
Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.