memory-manager

memory-manager is a skill for Claude Code, Codex from Orkas-AI/Orkas. It costs 2 tokens per session (735 once invoked), scanned A, original, MIT.

A protocol for saving durable context that should influence future conversations. It separates user preferences, project facts, and agent instructions from temporary task notes.

In plain words
What is it for?
Use it to decide what persistent information to save and where it belongs.
Why use it?
It prevents important long-term context from being stored in the wrong place or mixed with short-lived work.

Skill for Claude CodeCodex

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

Good fit Use it to decide what persistent information to save and where it belongs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orkas-ai/orkas/memory-manager
About the project

Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.

Orkas-AI/Orkas · 1,885 stars · on GitHub · orkas.ai

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 Orkas-AI/Orkas --skill memory-manager
Clone the repo
git clone --depth 1 https://github.com/Orkas-AI/Orkas

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 memory-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/orkas-ai/orkas/memory-manager/github.svg)](https://agentmods.dev/skills/orkas-ai/orkas/memory-manager)
Your own site
<a href="https://agentmods.dev/skills/orkas-ai/orkas/memory-manager"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/memory-manager/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.

agentmods 80×15 button for memory-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/orkas-ai/orkas/memory-manager"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/memory-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 735 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00002 $0.00735
Opus 5 $0.00001 $0.00367
Sonnet 5 $0.00000 $0.00147
Haiku 4.5 $0.00000 $0.00073

Measured 8d ago against content hash 6f6dc8f418c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

memory-manager 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.

resources/builtin/system/skills/memory-manager/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memory-manager

Use this protocol only for durable context that should affect future conversations. Do not persist current task progress, temporary plans, one-off status, or TODO and dependency state.

Choose the destination

Apply both axes: directive versus descriptive, and global versus project scope. Choose exactly one destination for each item unless the user explicitly requests two distinct durable records. Do not mirror descriptive knowledge into project instructions merely because later work should use that knowledge; "base future proposals on this fact" remains project memory, not a standing rule.

  • Use cross_session_memory with target: "agent" for Commander's durable orchestration lessons and user corrections about how Commander should coordinate, route, synthesize, or ask for missing information.
  • Use cross_session_memory with target: "user" for stable global user facts and preferences: identity, communication style, expertise, tech stack, or a preference that should apply outside the current project.
  • Use cross_session_memory with target: "shared" for stable non-user global facts, shared decisions and conventions, or repository and environment facts that every agent should know.
  • In a Project conversation, use cross_session_memory with target: "project" for durable descriptive project facts, decisions, outcomes, milestones, and conventions.
  • Use project_instructions for durable directives that should steer every future conversation in this project: its goal, scope, standing rules, and project-specific preferences or constraints.

Do not duplicate a global user preference or a descriptive project fact in project instructions. Do not put Commander-specific orchestration lessons in user or shared memory. Put concrete work items, live progress, and TODO status in project_tasks, not memory or project instructions.

Mutate safely

  1. Resolve the intended store, target, and current record. Use a read-only lookup when the exact record or current project instructions are not already identified; never invent a record identifier.
  2. Add new durable context, replace a correction to an existing record, and remove only an exact intended record. If several records match a replace or remove request, show the candidates and ask one concise clarifying question without mutating any of them.
  3. Treat project_instructions as a full replacement. Preserve every existing rule that still applies and send the complete intended text, not a partial patch.
  4. Write in the user's current UI language while preserving proper nouns, commands, paths, URLs, and exact quoted text.
  5. Name the exact tool, operation, and target even when tools are unavailable and you can only propose the mutation. A prose label such as "project memory" is not a substitute for cross_session_memory with target: "project".
  6. Call the exact mutation tool when available. Claim that a change succeeded only after its tool result confirms success; otherwise report the error or describe the intended mutation as a proposal.

Read the full file on GitHub · 31 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. 8d ago First seen · 31 lines · 2 tokens per session scan A 6f6dc8f418c5

Subscribe to this mod's changes

memory-manager is a skill published in the GitHub repository Orkas-AI/Orkas (1,885 stars, last pushed yesterday), licensed MIT. It adds 2 tokens to every session and 735 once invoked, about $0.0000 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 2026-09-03.

Related

Other skills, from other repositories

tutti-agent-workspace-app

Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…

tutti-os/tutti · 106 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

takt

A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.

nrslib/takt · 63 tokens

vellum-memory-v3-migration

One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.

vellum-ai/vellum-assistant · 63 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens

daily-briefing

Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…

vellum-ai/vellum-assistant · 75 tokens