What is agent-memory?

A three-level Markdown memory system for saving knowledge across coding sessions: shared project memory, memory for one agent, and memory for one conversation. Markdown is a plain-text format commonly used for documentation.

Use it when reading or writing memory files, deciding where a new insight belongs, or starting work that may depend on earlier context. It covers shared knowledge, agent-specific notes, conversation context, and automatic memory loading.

It prevents useful decisions and lessons from disappearing when a session ends while keeping private or temporary details in the right scope. The protocol also describes how memory is automatically provided to agents.

agent-memory — Skill for Claude Code by komluk/scaffolding

Install

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.

Any agent

npx skills add komluk/scaffolding --skill agent-memory

Clone the repo

git clone --depth 1 https://github.com/komluk/scaffolding

Made for: Claude Code.

Or install scaffolding, the plugin that ships this one along with the rest of its 39 skills, 9 commands, 13 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/komluk/scaffolding/agent-memory/github.svg)](https://agentmods.dev/skills/komluk/scaffolding/agent-memory)

Your own site

<a href="https://agentmods.dev/skills/komluk/scaffolding/agent-memory"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/agent-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/komluk/scaffolding/agent-memory"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/agent-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,527 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00071	$0.01527
Opus 5.5	$0.00028	$0.00611
Sonnet 5.5	$0.00014	$0.00305
Haiku 4.5	$0.00007	$0.00153

Measured 7d ago against content hash c2f424869868, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 7d 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.

skills/agent-memory/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Memory Protocol

3-tier persistent file-based memory under the repo-local .scaffolding/ directory, for cross-session knowledge accumulation. Vector memory (MCP tools) is covered by the semantic-memory-mcp skill.

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

The Conversation tier lives under .scaffolding/conversations/, which is a symlink to <share>/projects/<repo-name>/conversations (shared across machines). Paths are unchanged; always go through the symlink.

How Memory Is Read

No hook or pipeline injects these files into agent context -- they are read on demand (see On First Turn). The conversation tier is the inter-agent handoff: a downstream agent in the same chain reads what an upstream agent recorded there.

On First Turn

Before starting work, read available memory (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_id is 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/

Read the full file on GitHub · 141 lines

Changes

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.

7d ago Changed · -5 lines · +1 tokens per session c2f424869868
8d ago Changed · +2 lines 5f78fdf38cf3
1mo ago First seen · 144 lines · 70 tokens per session scan A 29c1ff1c13f7

Subscribe to this mod's changes

agent-memory is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,527 once invoked, about $0.0003 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.

Claude Code Memory and context ai-agents claude-code-plugin claude-plugin developer-tools multi-agent-orchestration

save

Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.

XTSoftwareLabs/neatcontext-plugins · 49 tokens

import

Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.

XTSoftwareLabs/neatcontext-plugins · 54 tokens

agent-memory