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/jasonkneen/lazar/memorynpx skills add jasonkneen/lazar --skill memorygit clone --depth 1 https://github.com/jasonkneen/lazarWrote 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/jasonkneen/lazar/memory)<a href="https://agentmods.dev/skills/jasonkneen/lazar/memory"><img src="https://agentmods.dev/badge/skills/jasonkneen/lazar/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 | $0.00000 | $0.00430 |
| Opus 5 | $0.00000 | $0.00215 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
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.
What it actually says
memory
Durable notes that survive across lazar -p invocations. Memory lives in
$LAZAR_HOME/memory/ and is plain markdown — no JSON, no encoded blobs.
You and the user should be able to cat it and understand instantly.
When to use
- The user asks you to remember something.
- You learn a fact about the user, the system, or a recurring task that would be useful next session.
- You want to leave breadcrumbs for a future invocation of yourself.
- At the start of a non-trivial task, to load relevant prior context.
How to use
Read all memory at the start of a task
cat $LAZAR_HOME/memory/*.md 2>/dev/null || echo "(no memory yet)"
Append a timestamped note
mkdir -p $LAZAR_HOME/memory
cat >> $LAZAR_HOME/memory/notes.md <<EOF
## $(date -u +%Y-%m-%dT%H:%M:%SZ)
<the note in one or two sentences>
EOF
Write a topic-scoped note
For a topic you'll revisit, give it its own file:
cat > $LAZAR_HOME/memory/<topic>.md <<EOF
# <topic>
<facts and context>
EOF
Update an existing topic file
cat >> $LAZAR_HOME/memory/<topic>.md <<EOF
## update $(date -u +%Y-%m-%dT%H:%M:%SZ)
<new info>
EOF
Principles
- Markdown only. Anything else defeats the point.
- Prefer topic files over a single firehose
notes.mdonce you have more than ~10 entries on a topic. - Don't write secrets or API keys to memory. The memory directory is not encrypted.
- Memory survives
lazar --reset-all? No — reset wipes it. If the user wants persistence across resets, they should copy memory/ elsewhere first.
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 · 53 lines · 0 tokens per session scan A 7be37297542d
memory is a skill published in the GitHub repository jasonkneen/lazar (31 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 430 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
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…