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 lsaint/aikito --skill durable-memorygit clone --depth 1 https://github.com/lsaint/aikitoWrote 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/lsaint/aikito/durable-memory)<a href="https://agentmods.dev/skills/lsaint/aikito/durable-memory"><img src="https://agentmods.dev/badge/skills/lsaint/aikito/durable-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/lsaint/aikito/durable-memory"><img src="https://agentmods.dev/badge/skills/lsaint/aikito/durable-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.01110 |
| Opus 5.5 | $0.00021 | $0.00444 |
| Sonnet 5.5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Durable Memory
This bundled skill is a system-managed snapshot of the installed Aikito package. Do not customize it in place; put additional memory policy in global or project instructions.
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/runtime entry in registered projects.
Each scope stores atomic notes under notes/. These files are the complete source of truth; no separate index is required. .agents/memory/ is only a runtime entry point and keeps no independent copy; all memory operations act directly on the canonical notes 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.
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.
- 1mo ago Changed · +4 lines f1a81dce72f5
- 1mo ago Changed 915b251eb90f
- 1mo ago First seen · 72 lines · 53 tokens per session scan A a6fc621b3b8b
durable-memory is a skill published in the GitHub repository lsaint/aikito (134 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,110 once invoked, about $0.0002 per session on Opus 5.5. 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
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for CodeBuddy. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for Hermes Agent. Store facts, recall past knowledge, link related memories, manage lifecycle.