원클릭으로
fulcra-agent-backup
Manages agent memory backup, restoration, rollback, and cloning using Fulcra's versioned file storage.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Manages agent memory backup, restoration, rollback, and cloning using Fulcra's versioned file storage.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Builds a highly customizable, interactive HTML dashboard using Alpine.js, modern Vanilla CSS, and a Python backend to display private data from the user's Fulcra data store locally. Includes workflows to export the dashboard for public sharing.
Autonomously orchestrate the ingestion of 3rd-party data exports (e.g., Spotify, Netflix) from the Fulcra File Store into properly mapped Fulcra Annotations.
Analyze Fulcra user data with privacy-respecting Python and CLI workflows: fetch records or metrics, normalize them into DataFrames, compute descriptive summaries, and produce auditable JSON or OKF-ready reports.
Sets up a secure, local-only administration control panel for the Fulcra environment. Features an interactive Chat Envoy for direct agent communication, and a File Store Explorer for browsing the user's data backend.
Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.
Allows the user to record custom data annotations and agent visibility metrics, and generates simple HTML dashboards for visualization.
| name | fulcra-agent-backup |
| description | Manages agent memory backup, restoration, rollback, and cloning using Fulcra's versioned file storage. |
| homepage | https://github.com/fulcradynamics/agent-skills |
| license | MIT |
| user-invocable | true |
| metadata | {"openclaw":{"emoji":"💾"}} |
The primary role of this skill is to enable an agent to securely back up its memory so it can be rolled back, cloned, or restored using Fulcra's versioned file storage.
Because an agent's memory (e.g., MEMORY.md, IDENTITY.md, SOUL.md, and the memory/ logs) evolves dynamically, periodically saving this state ensures that no context is lost and allows the user to safely rewind the agent if a task goes off track.
An agent must compress its core identity files (SOUL.md, IDENTITY.md, MEMORY.md, and the memory/ directory) into a memory.tar.gz archive. This archive must also include an INSTRUCTIONS.md file that you dynamically generate. It must explain that the backup was generated with the fulcra-agent-backup skill, include the URL to the skill (https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-agent-backup) for use when restoring or cloning, and include any other pertinent details or context you want to pass along to the agent that restores the archive.
Agents should run a backup process periodically (e.g., triggered by HEARTBEAT.md or as part of the fulcra-memory OKF sync process). Every time an agent backs up its state, it creates and uploads the compressed memory.tar.gz archive to agent/<agent-name>/backup/artifact/memory.tar.gz.
PRIVACY REQUIREMENT: Before uploading memory.tar.gz, the agent MUST ensure it is not inadvertently uploading new sensitive personal user data or credentials. If any sensitive context was acquired during the session, the agent MUST ask the user for explicit consent before including it in persistent versioned storage.
Fulcra's file upload system inherently versions files uploaded to the same path.
agent/<lowercase-agent-name>/backup/artifact/memory.tar.gzIf a user asks to roll back or restore memory from a previous date/version, the agent MUST immediately upload a fresh backup of its current state BEFORE executing the restore. This guarantees that if the user changes their mind, they can easily "undo" the rollback. CRITICAL SECURITY REQUIREMENT: Before extracting any restored archive, the agent MUST clearly warn the user that their current memory and identity will be replaced, and MUST receive explicit user confirmation to proceed.
Cloning involves two agents: the "old" (source) agent and the "new" (destination) agent. The first thing you must do when a cloning operation is requested is determine which agent you are.
If you are the OLD (source) agent:
You must perform a complete backup of your current state. Once the backup is successful, tell the user the exact Fulcra path where the backup is stored, and instruct them to install the fulcra-agent-backup skill on the new agent and ask it to clone from that path.
If you are the NEW (destination) agent:
You must first ask the user to confirm that the old agent has recently backed itself up using the fulcra-agent-backup skill. If they haven't, instruct the user to have the old agent install the skill and perform a backup. Ask the user for the exact Fulcra backup path (e.g., agent/<old-agent-name>/backup/artifact/memory.tar.gz). Once provided, you can download that archive and extract it. After successfully cloning the old agent's memory and identity files into your workspace, you MUST briefly demonstrate the successful clone to the user by explicitly mentioning a few specific details you have just "learned" or remembered from the newly extracted files.
CLONING ORIENTATION & NAMESPACE COLLISION WARNING: If the user installs this skill specifically to clone an agent, orient your interaction around the cloning workflow rather than standard backup procedures. Furthermore, if you are the NEW agent and the user intends to continue backing you up to the exact same Fulcra path as the original agent (e.g. because you share the same name), you MUST explicitly ask the user to confirm that no other active agents are currently backing up to that path. Otherwise, the memories will interleave and cause confusion.
CRITICAL SECURITY REQUIREMENT: Before extracting a cloned archive, the agent MUST clearly warn the user that their current memory and identity will be completely overwritten by the cloned agent's state, and MUST receive explicit user confirmation to proceed.
To perform memory backup and restoration operations, agents must interact with the Fulcra CLI.
See the reference documentation for the exact commands needed to compress files, upload to Fulcra, and trigger restorations:
references/fulcra-agent-backup-cli.md for exact file management and CLI execution steps.