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 skills add ag2ai/ag2-skills --skill ag2-knowledge-and-memorygit clone --depth 1 https://github.com/ag2ai/ag2-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/ag2ai/ag2-skills/ag2-knowledge-and-memory)<a href="https://agentmods.dev/skills/ag2ai/ag2-skills/ag2-knowledge-and-memory"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-knowledge-and-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ag2ai/ag2-skills/ag2-knowledge-and-memory"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-knowledge-and-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00193 | $0.04253 |
| Opus 5 | $0.00097 | $0.02126 |
| Sonnet 5 | $0.00039 | $0.00851 |
| Haiku 4.5 | $0.00019 | $0.00425 |
Grade A, and why
ag2-knowledge-and-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 10d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge, memory, and context assembly
This skill covers three related primitives that work together:
| Primitive | Lives in | Role |
|---|---|---|
KnowledgeStore |
ag2.knowledge |
Path-based persistent storage (memory / sqlite / disk / redis) |
| Assembly policies | ag2.policies |
Shape (prompts, events) per turn before the LLM call |
| Aggregation / Compaction | ag2.aggregate / .compact |
Write structured knowledge to the store / trim event history |
KnowledgeConfig wires all three onto an Agent via the knowledge= constructor parameter; assembly policies go via assembly=.
When to use what
| User intent | Reach for |
|---|---|
| Remember user preferences / state between conversations | WorkingMemoryAggregate + WorkingMemoryPolicy (and a persistent store) |
| Summarise each session for next time | ConversationSummaryAggregate + EpisodicMemoryPolicy |
| Hard-cap event history sent to the LLM | SlidingWindowPolicy(max_events=N) |
| Cap by approximate token count | TokenBudgetPolicy(max_tokens=N) |
| Drop lifecycle / observer events from the LLM's view | ConversationPolicy() |
| Trim stream history (not just LLM view) | TailWindowCompact or SummarizeCompact |
| Route observer alerts to the LLM | AlertPolicy() |
60-second recipe — persistent working memory
from ag2 import Agent, KnowledgeConfig
from ag2.aggregate import AggregateTrigger, WorkingMemoryAggregate
from ag2.config import OpenAIConfig
from ag2.knowledge import DiskKnowledgeStore
from ag2.policies import ConversationPolicy, WorkingMemoryPolicy
store = DiskKnowledgeStore("./journal-state")
config = OpenAIConfig(model="gpt-5")
agent = Agent(
"journal",
prompt="You are a daily journal companion.",
config=config,
knowledge=KnowledgeConfig(
store=store,
aggregate=WorkingMemoryAggregate(config=config),
aggregate_trigger=AggregateTrigger(on_end=True),
),
assembly=[
WorkingMemoryPolicy(), # injects /memory/working.md on every LLM call
ConversationPolicy(),
],
)
What ships with it
2 files 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.
- 10d ago First seen · 274 lines · 193 tokens per session scan A 07ed332a2f46
ag2-knowledge-and-memory is a skill published in the GitHub repository ag2ai/ag2-skills (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 193 tokens to every session and 4,253 once invoked, about $0.0010 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…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.