agent-memory

agent-memory is a skill for Claude Code, Codex from ipiton/agent-memory-mcp. It costs 30 tokens per session (1,593 once invoked), scanned A, original, MIT.

A system for keeping useful project information between agent sessions through persistent memory. It stores decisions, procedures, incidents, postmortems, and current work context.

In plain words
What is it for?
It helps record architecture decisions, deployment or debugging procedures, known problems, incidents, and the current state of a task.
Why use it?
It prevents important project context from being lost when a session ends and helps recover relevant information later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps record architecture decisions, deployment or debugging procedures, known problems, incidents, and the current state of a task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ipiton/agent-memory-mcp/agent-memory
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 ipiton/agent-memory-mcp --skill agent-memory
Clone the repo
git clone --depth 1 https://github.com/ipiton/agent-memory-mcp

Made for: Claude Code, Codex.

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 agent-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/ipiton/agent-memory-mcp/agent-memory.svg)](https://agentmods.dev/skills/ipiton/agent-memory-mcp/agent-memory)
Your own site
<a href="https://agentmods.dev/skills/ipiton/agent-memory-mcp/agent-memory"><img src="https://agentmods.dev/badge/skills/ipiton/agent-memory-mcp/agent-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,593 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01593
Opus 5 $0.00015 $0.00796
Sonnet 5 $0.00006 $0.00319
Haiku 4.5 $0.00003 $0.00159

Measured 2d ago against content hash dfeda5d5e1c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 2d 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.

docs/examples/agent-memory-skill.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Состояние Памяти (Memory State)

У тебя есть доступ к persistent memory через MCP-инструменты. Твоя задача — поддерживать актуальность "Банка Проекта" (Project Bank), минимизируя шум.

Когда сохранять (store_memory):

  • Принято архитектурное решение: тип semantic, важность 0.9.
  • Выработан рабочий процесс: деплой, тесты, специфичный debug — тип procedural, важность 0.8.
  • Найден баг или ограничение: описание решения и причин — тип episodic, важность 0.7.
  • Текущий контекст задачи: над чем работаем в данный момент — тип working, важность 0.5.

Специализированные типы:

  • Архитектурное решение: используй store_decision с rationale и consequences.
  • Инцидент: используй store_incident с impact, root cause, severity.
  • Runbook: используй store_runbook с procedure, trigger, verification, rollback.
  • Postmortem: используй store_postmortem с root cause и action items.

Когда вспоминать (recall_memory):

  • Начало новой сессии: вызови summarize_project_context или project_bank_view view=canonical_overview для восстановления рабочего контекста.
  • Перед изменением инфраструктуры: проверь search_runbooks и recall_similar_incidents на наличие рисков.
  • При вопросе "как делать X": поиск по типу procedural.
  • При вопросе "почему так решили": используй recall_canonical_knowledge или project_bank_view view=decisions.

Жизненный цикл сессии (Session Lifecycle)

1. Start-of-session Recall

Перед началом работы ты обязан восстановить контекст:

  • Используй project_bank_view view=canonical_overview для верхнеуровневого понимания.
  • Изучи недавние изменения в сервисах или компонентах, которые предстоит затронуть.
  • Найди релевантные RFC, заметки о инцидентах или чейнджлоги через semantic_search.
  • Проверь steward_status — есть ли pending review items или недавние findings.

2. In-session Patterns

  • Решения фиксируй сразу через store_decision — не откладывай на конец сессии.
  • Длинные трейсы и логи — store_memory (episodic), в чат только 5-8 строк.
  • Перед исследованием файлов — сначала recall_memory по теме, чтобы не искать заново.

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 30 tokens per session scan A dfeda5d5e1c0

Subscribe to this mod's changes

agent-memory is a skill published in the GitHub repository ipiton/agent-memory-mcp (42 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,593 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 2026-09-05.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens