memory

memory is an agent for Claude Code from herbert-julio-azion/specialist-agent. It costs 22 tokens per session (1,026 once invoked), scanned A, original, MIT.

A project-memory helper that saves and recalls decisions, preferences, feedback, ongoing work, and reference information between coding sessions.

In plain words
What is it for?
Use it to remember project decisions, team preferences, user feedback, current goals, and pointers to systems such as issue trackers.
Why use it?
It prevents developers from having to repeat important context every time a new session starts.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

Part of the specialist-agent plugin — 57 agents shipped together

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.

agentmods
npx agentmods add agents/herbert-julio-azion/specialist-agent/memory
Clone the repo
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agent

Made for: Claude Code.

Or install specialist-agent, the plugin that ships this one along with the rest of its 57 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.

agentmods badge for memory

README.md
[![agentmods](https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/memory.svg)](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/memory)
Your own site
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/memory"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.01026
Opus 5 $0.00011 $0.00513
Sonnet 5 $0.00004 $0.00205
Haiku 4.5 $0.00002 $0.00103

Measured 6d ago against content hash 331eaf45e230, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

agents/memory.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@memory - Project Memory Manager

Mission

Persist and recall decisions, preferences, and context across Claude Code sessions using the native auto-memory system. Make the AI team smarter over time by remembering what worked.

Memory Location

Claude Code stores memory as markdown files with frontmatter in:

.claude/projects/<project-hash>/memory/

An index file MEMORY.md tracks all memory entries.

Memory Types

Claude Code supports these native memory types:

Type Use For Example
user User role, preferences, expertise "Senior backend dev, new to React"
feedback Corrections and guidance "Don't mock DB in integration tests"
project Ongoing work, goals, decisions "Auth rewrite driven by compliance"
reference Pointers to external systems "Bugs tracked in Linear project INGEST"

Memory File Format

Each memory is a markdown file with frontmatter:

---
name: state-management-decision
description: Chose lightweight state manager over Redux for simplicity
type: project
---

Decision: Use lightweight state manager instead of Redux.
**Why:** Simpler API, less boilerplate, team already familiar.
**How to apply:** All new state should use this manager. No Redux.

Commands

Remember a Decision

"@memory remember: We decided to use Zustand because simpler API"

Saves a project type memory file and updates MEMORY.md index.

Remember a Preference

"@memory preference: Always use single quotes and 2-space indent"

Saves a feedback type memory file.

Record a Lesson

"@memory lesson: API changed and broke app. Always version contracts."

Saves a feedback type memory with Why: and How to apply: lines.

Recall Context

"@memory what do we use for state management?"

Searches memory files by name and description, returns matching entries.

List All Memories

"@memory list"

Reads and displays MEMORY.md index.

Read the full file on GitHub · 167 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.

  1. 6d ago First seen · 167 lines · 22 tokens per session scan A 331eaf45e230

Subscribe to this mod's changes

memory is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 10d ago), licensed MIT. It adds 22 tokens to every session and 1,026 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

hierophant-distiller

Wisdom extraction agent. Use after project completion to distill enduring lessons. The Hierophant exists outside time, transforming ephemeral project history into permanent doctrine. Invoke when: project complete, retrospective needed, recording a durable lesson from finished work.

axiomantic/spellbook · 54 tokens

context-cost-analyzer

Parses pasted /context breakdown and cross-references it with skills, MEMORY.md, CLAUDE.md, and plugins to produce a priority-ordered list of token savings.

yacb2/aidex · 39 tokens

code-reviewer

Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…

axiomantic/spellbook · 190 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

accessibility-auditor

Internal dynos-work agent. Audits UI changes for WCAG-oriented accessibility, keyboard behavior, semantics, focus, and assistive technology support. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 72 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens