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/itallstartedwithaidea/agent-skills/entity-memory-managementnpx skills add itallstartedwithaidea/agent-skills --skill entity-memory-managementgit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote 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/itallstartedwithaidea/agent-skills/entity-memory-management)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/entity-memory-management"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/entity-memory-management.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 | $0.00036 | $0.02872 |
| Opus 5 | $0.00018 | $0.01436 |
| Sonnet 5 | $0.00007 | $0.00574 |
| Haiku 4.5 | $0.00004 | $0.00287 |
Grade A, and why
entity-memory-management 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.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entity Memory Management
Part of Agent Skills™ by googleadsagent.ai™
Description
Entity Memory Management is the systematic extraction, persistence, and retrieval of named entities across agent sessions, enabling long-term contextual awareness that transforms transient conversations into persistent relationships. While generic memory systems store session summaries, entity memory operates at a granular level — tracking specific campaigns, metrics, decisions, user pain points, and preferences as discrete, queryable objects. This precision enables agents to recall that "Campaign Alpha switched to Target CPA last Tuesday" rather than merely "we discussed bidding changes recently."
This skill is the production entity memory architecture powering Buddy™ at googleadsagent.ai™, where entity memory tracks thousands of named entities across hundreds of user sessions. The system maintains entities of defined types — campaigns (with their strategies, budgets, and performance trajectories), metrics (specific KPIs and their historical values), decisions (changes made and their rationale), and pain points (recurring issues the user has expressed frustration about). Each entity is extracted, typed, scored for importance, stored in Cloudflare KV, and retrieved contextually in future sessions.
The result is an agent that genuinely "remembers" its users — not through conversation replay, but through structured, typed knowledge that persists and evolves. This creates a fundamentally different user experience where the agent builds on prior context rather than starting fresh.
Use When
- The agent serves repeat users who expect continuity across sessions
- Domain entities (campaigns, accounts, projects) need tracking over time
- Decisions made in past sessions should inform future recommendations
- User preferences and pain points should persist without re-explanation
- You need to detect trends across sessions (improving metrics, recurring issues)
- Compliance or audit requirements demand a structured record of agent-user interactions
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 · 316 lines · 36 tokens per session scan A 63a0553420cf
entity-memory-management is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (36 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 2,872 once invoked, about $0.0002 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.
Other skills, from other repositories
supermemory
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…
misakanet-failure-memory
Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network.
titen-memory
Use the Titen MCP server to recall bounded evidence-grounded context, record verified durable signals, submit feedback, and coordinate checkpoints, leases, or handoffs. Use when work may benefit from prior project memory or when a verified outcome should be preserved for another agent; do not use it to capture raw…
NorthwoodsSubstrate
Persistent memory store — second brain backed by D1 on user's own CF account. Save and retrieve entries across sessions and devices. USE WHEN need to remember, recall, search past notes, save a thought, look up what user said earlier, store a decision, find a breadcrumb. NOT FOR ephemeral session state (use…
NorthwoodsResume
Session-start momentum restart — one forward-leaning sentence answering 'where was I.' Never reports timestamps, never lists incomplete tasks, never states a verdict. Restarts momentum, does not audit absence. USE WHEN session start, picking back up, where was I, resume work, getting back to it. NOT FOR status reports…
review-claude-code
Claude Code setup review (settings.json, permissions, rules, hooks, agents, memory, worktrees) against current official best practices. USE WHEN: user runs /review-claude-code or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.