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/komluk/scaffolding/agent-memorynpx skills add komluk/scaffolding --skill agent-memorygit clone --depth 1 https://github.com/komluk/scaffoldingWrote 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/komluk/scaffolding/agent-memory)<a href="https://agentmods.dev/skills/komluk/scaffolding/agent-memory"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/agent-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 | $0.00070 | $0.01506 |
| Opus 5 | $0.00035 | $0.00753 |
| Sonnet 5 | $0.00014 | $0.00301 |
| Haiku 4.5 | $0.00007 | $0.00151 |
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 3d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Protocol
3-tier persistent memory system for cross-session knowledge accumulation.
Memory Tiers
| Tier | Path | Scope | Written By | Read By |
|---|---|---|---|---|
| Shared | .scaffolding/agent-memory/shared/KNOWLEDGE.md |
Whole project | Any agent | All agents |
| Agent | .scaffolding/agent-memory/agents/{agent-name}/MEMORY.md |
Per agent | Owning agent | Own agent + architect |
| Conversation | .scaffolding/conversations/{conversation_id}/agent-memory/context.md |
Per conversation | Any agent in conversation | Agents in same conversation |
Automatic Injection
Memory is auto-injected into agent context via recall_for_agent() in the task execution pipeline. When a task starts, the system reads:
.scaffolding/agent-memory/shared/KNOWLEDGE.md(always).scaffolding/agent-memory/agents/{agent-name}/MEMORY.md(when agent_name is known).scaffolding/conversations/{id}/agent-memory/context.md(when conversation_id is provided)
This means agents receive memory context automatically. Manual reading on first turn is optional but recommended for verifying latest data.
On First Turn
Before starting work, optionally read available memory for latest content (skip if files don't exist):
- Read
.scaffolding/agent-memory/shared/KNOWLEDGE.md - Read
.scaffolding/agent-memory/agents/{your-agent-name}/MEMORY.md - If
conversation_idis provided in task context: Read.scaffolding/conversations/{conversation_id}/agent-memory/context.md
Before Completing
Write significant findings to the appropriate tier:
Shared Knowledge (KNOWLEDGE.md)
Save here:
- Project architecture facts confirmed across multiple tasks
- Deployment gotchas and infrastructure quirks
- Cross-cutting patterns (e.g. how Redis is used, how tasks flow)
- Known bugs or limitations that affect multiple agents
Do NOT save:
- Agent-specific patterns (use agent memory)
- Task-specific context (use conversation memory)
- Anything already in CLAUDE.md or docs/
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.
- 3d ago First seen · 144 lines · 70 tokens per session scan A 29c1ff1c13f7
agent-memory is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed 28d ago), licensed MIT. It adds 70 tokens to every session and 1,506 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
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
brand-setup
Create or update the brand profile every other skill reads — a quick 5-question or full 17-question interactive setup capturing identity, business model, industry and compliance markets, 4-dimension voice scales, channels, goals, and competitors, saved to /.claude-marketing/brands/{slug}/profile.json via…
spring-security-jwt
Use when an application issues and validates its own first-party JWT access and refresh tokens, including authentication filters, password encoding, RBAC, and method security. For JWTs issued by Keycloak, Auth0, Okta, Cognito, or another authorization server, use oauth2-resource-server.
spring-ai-integration
Use when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI ChatClient, prompt templates, embeddings, vector stores, and structured output. Use when user mentions Spring AI, LLM, ChatGPT, Claude, RAG, embeddings.
mcp-server
Use when exposing Spring Boot 3 application capabilities through Model Context Protocol tools, resources, or prompts. Covers Spring AI 1.x tool callback registration, transports, schemas, errors, security, and standalone MCP Java SDK compatibility.