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 VoDaiLocz/kilo-kit-mcp --skill agent-memorygit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote 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/vodailocz/kilo-kit-mcp/agent-memory)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/agent-memory"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/agent-memory.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 15 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00042 | $0.00959 |
| Opus 5 | $0.00021 | $0.00479 |
| Sonnet 5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
agent-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 8d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Framework
Overview
The agent-memory skill provides a standardized architectural approach to building intelligent memory systems for agents within the KILO-KIT ecosystem. It bridges the gap between ephemeral context windows and durable, long-term storage, enabling agents to maintain user preferences, project-specific conventions, and debugging history across multiple sessions.
When To Use
- When designing systems that must persist state across independent interaction sessions.
- When an agent needs to manage large volumes of user-specific facts that exceed the context window.
- When implementing self-managed memory tools (MemGPT/Letta patterns) to allow agents to control their own knowledge base.
- When building systems requiring automatic entity updates (Mem0 pattern) to resolve conflicting or stale information.
Core Concepts
- Memory Hierarchy: Differentiating between transient working context and persistent knowledge.
- Fact Extraction: Identifying core entities, preferences, and relationships from conversational flow.
- Supersession: Automatically replacing outdated facts with new information to maintain "ground truth."
- Temporal Validity: Tracking the lifespan and relevance of memory entries over time.
- Persistence: Ensuring data survives agent resets or session termination.
Memory Architecture
The framework defines four distinct tiers of memory:
- Working Context (RAM): The immediate token window. Ephemeral, high-speed, and limited in capacity.
- Episodic Memory: Logged history of past interactions, enabling agents to query "what we discussed last time."
- Semantic Vector Store: Long-term storage for semantic concepts, documentation snippets, and project conventions, retrieved via similarity search.
- Archival Storage (Disk): Cold storage for large documents or historical artifacts that are rarely needed but must be maintained.
Implementation Patterns
Fact Extraction & Supersession (Mem0 Pattern)
- Implement extraction loops that analyze messages for key-value pairs (e.g.,
user_preference: dark_mode). - When a new fact conflicts with an old one, perform an "update" (supersession) rather than appending duplicates. This ensures the agent always acts on the most recent truth.
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.
- 8d ago First seen · 74 lines · 42 tokens per session scan A ded7772c64b2
agent-memory is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 959 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
memb-skill
BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectures, and developer patterns across tasks.
agent-memory-mcp
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
knowledge-graph-management
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph.
dpf-elicit-tacit-knowledge
Use when durable DPF knowledge lives only in a human's head — a decision rationale, the why behind a choice, a profession technique, domain context a build depends on.