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/lsaint/aikito/durable-memorynpx skills add lsaint/aikito --skill durable-memorygit clone --depth 1 https://github.com/lsaint/aikitoWhat 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 | $0.00053 | $0.01097 |
| Opus 5 | $0.00026 | $0.00549 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
durable-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 2d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Durable Memory
Objective
Reduce redundant investigation and repeated pitfalls using a minimal, trustworthy, and searchable memory store.
Memory is a decision-support layer, not a transcript or activity log. Optimize for future decision value rather than completeness, and prefer omission over low-confidence memory.
Decide autonomously when to retrieve, follow related knowledge, or persist. This skill is not a rigid step-by-step procedure: never read or write merely for compliance, and exercise restraint when value is uncertain.
Scope & Single Source of Truth
Resolve <workspace> with aikito path workspace. All memory lives there under Git:
- Global Memory —
<workspace>/memory/: cross-project experience, user preferences, general engineering patterns. Always available. - Project Memory —
<workspace>/projects/<project-name>/memory/: project-specific constraints, historical architecture decisions, project-unique debugging lessons. Usually reached through the.agents/memory/symlink in registered projects.
Each scope holds an index.md navigation entry and a notes/ directory of atomic notes. .agents/memory/ is only a runtime entry point and keeps no independent copy; all memory operations act directly on the canonical files above.
Decision Principles
Retrieve proactively when historical knowledge could materially affect judgment (familiar modules, recurring issues, user preferences, architecture constraints, past decisions). Read only what is relevant to the current task; never load all memories by default.
Knowledge is usually worth persisting when it is likely to matter again, changes future judgment, and is not trivial to recover from the current environment. Prefer verified knowledge; explicit user decisions and preferences are authoritative for their own scope.
Do NOT record:
- Temporary debugging outputs, transient task progress, or modified file lists.
- Unverified hypotheses or rapidly shifting guesses.
- Facts easily readable from current codebase inspection.
- Passwords, tokens, API keys, or other sensitive credentials.
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.
- 2d ago First seen · 72 lines · 53 tokens per session scan A a6fc621b3b8b
durable-memory is a skill published in the GitHub repository lsaint/aikito (80 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 1,097 once invoked, about $0.0003 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
create-skill
Wizard for creating new Agent Zero skills. Guides users through creating well-structured SKILL.md files. Use when users want to create custom skills.
generating-mod-envs
Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for /mods learn --env; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative…
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
memory-curation
When you have read / processed a workspace asset in this session and learned something durable about it, write a memory page so future sessions benefit. Maintain the workspace wiki's hierarchical structure as it grows.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.