New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Memory Fork

by Ghost-xDD in Ghost-xDD/memforks

Fork agent memory into parallel branches to explore competing hypotheses.

Custom licenceAuto-check passedAgent Workflows

Install Memory Fork

skills CLI
$ npx skills add Ghost-xDD/memforks --skill memory-fork -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ghost-xDD/memforks memory-fork --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ghost-xDD/memforks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codex/plugins/memforks/skills/memory-fork .claude/skills/memory-fork && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memory-fork
GitHub stars
105
Token cost
~1.1k tokens
SKILL.md length
479 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Custom licence

At a glance

Fork agent memory into parallel branches to explore competing hypotheses.

  • Works in 5 steps: Announce the fork → Create the branches → Investigate hypothesis A → …
  • More genuinely competing approaches worth testing in isolation — whether the user names them explicitly (explore both
  • SKILL.md covers When to trigger, Procedure, Output format for each commit and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory Fork is an agent skill from Ghost-xDD/memforks. Fork agent memory into parallel branches to explore competing hypotheses. Use whenever a task has two or more genuinely competing approaches worth testing in isolation — whether the user names them explicitly ("explore both", "compare A vs B") OR asks an open decision question (e.g. "what's the fastest way to X?") where you can identify two credible, mutually-exclusive solutions.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent memory. The repository describes itself as: Git for AI agent memory.

When your agent uses it

  • More genuinely competing approaches worth testing in isolation — whether the user names them explicitly (explore both
  • Compare A vs B) OR asks an open decision question (e.g

Example prompts

  • “explore both”
  • “compare A vs B”
  • “s the fastest way to X?”
  • “/memory-fork”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Announce the fork
  2. Create the branches
  3. Investigate hypothesis A
  4. Investigate hypothesis B
  5. Summarise

What it can do on your machine

Read from SKILL.md and the folder at commit 314b207. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory Fork loads about 1.1k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 479 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 479 words (~1,117 tokens).

“Fork the MemForks memory tree whenever a task has two or more genuinely competing approaches that deserve to be tested in isolation. Never collapse competing ideas into a single stream. The decision to fork is yours — you do not…”

— opening of SKILL.md by Ghost-xDD, Custom licence
name
memory-fork

Read the full SKILL.md on GitHub

Files

Just SKILL.md in plugins/codex/plugins/memforks/skills/memory-fork of Ghost-xDD/memforks.

Open the folder on GitHubat commit 314b207

Compare with similar skills

Memory Fork next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memory Fork compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory Fork this skillGhost-xDD/memforks105—~1.1kAutomated safety check: PassCustom licence
Coding Agent Session Findercode-yeongyu/oh-my-openagent70k1 repos~2.8kAutomated safety check: PassCustom licence
Claude-Mem Cloud Syncthedotmack/claude-mem98k1 repos~1kAutomated safety check: NotesApache-2.0
Cognee CLI Memory Commandstopoteretes/cognee32k1 repos~2.2kAutomated safety check: NotesApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Claude-Mem Searchthedotmack/claude-mem98k1 repos~511Automated safety check: PassApache-2.0

Similar skills

  • Coding Agent Session Finder

    code-yeongyu/oh-my-openagent

    Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.

    70k GitHub starsUsed in 1 repo~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude-Mem Cloud Sync

    thedotmack/claude-mem

    Checks claude-mem cloud sync status and guides you through connecting a cmem.ai Pro account without the sync token ever passing through the chat.

    98k GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes

  • Cognee CLI Memory Commands

    topoteretes/cognee

    Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

    32k GitHub starsUsed in 1 repo~2.2k tokens
    Agent WorkflowsAuto-check: notes

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Claude-Mem Search

    thedotmack/claude-mem

    Searches the user's persistent cross-session memory for timestamped observations synthesized from past agent sessions on cmem.ai.

    98k GitHub starsUsed in 1 repo~511 tokens
    Agent WorkflowsAuto-check passed

  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from Ghost-xDD/memforks

  • Memforks Status

    Ghost-xDD/memforks

    Show MemForks on-chain status: branch DAG, open merge proposals, recent commits.

    105 GitHub stars~755 tokensUpdated 1 mo ago
    Auto-check passed

  • Memory Commit

    Ghost-xDD/memforks

    Commit facts to the MemForks memory DAG using memfork commit --facts.

    105 GitHub stars~679 tokensUpdated 1 mo ago
    Auto-check passed

  • Memory Recall

    Ghost-xDD/memforks

    Recall relevant memory for the current task using the MemWal MCP tool.

    105 GitHub stars~444 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Memory Fork

What does Memory Fork do?

Fork agent memory into parallel branches to explore competing hypotheses. Memory Fork is an agent skill from Ghost-xDD/memforks. Fork agent memory into parallel branches to explore competing hypotheses.

When should I use Memory Fork?

Memory Fork fits situations like: more genuinely competing approaches worth testing in isolation — whether the user names them explicitly (explore both; compare A vs B) OR asks an open decision question (e.g.

How do I install Memory Fork in Claude Code?

Run `npx skills add Ghost-xDD/memforks --skill memory-fork -a claude-code`. Or copy the skill folder (plugins/codex/plugins/memforks/skills/memory-fork in Ghost-xDD/memforks) into .claude/skills/memory-fork in your project. Claude Code loads it when a task matches its description.

How do I install Memory Fork in Codex?

Run `npx skills add Ghost-xDD/memforks --skill memory-fork -a codex`. Or copy the skill folder (plugins/codex/plugins/memforks/skills/memory-fork in Ghost-xDD/memforks) into .agents/skills/memory-fork in your project. Codex loads it when a task matches its description.

Can I use Memory Fork in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ghost-xDD/memforks --skill memory-fork -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-fork, .gemini/skills/memory-fork, .github/skills/memory-fork and .opencode/skills/memory-fork in your project.

What does Memory Fork need to run?

SKILL.md names no scripts, command-line tools or credentials: Memory Fork is instructions for the agent only.

Does Memory Fork access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Memory Fork safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Memory Fork use?

Memory Fork has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Memory Fork use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory Fork?

Skills that share tags, products or a category with Memory Fork: Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Claude-Mem Cloud Sync (thedotmack/claude-mem, 98k stars), Cognee CLI Memory Commands (topoteretes/cognee, 32k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Fork?

Ghost-xDD (a GitHub user) maintains it in Ghost-xDD/memforks, which has 105 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 28, 2026.

Source: Ghost-xDD/memforks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.