memory · 0xsteph — Claude Code command: what it does, how to install
Updates the .claude/PROJECT_MEMORY.md file with session decisions and pending tasks without losing past context.
MIT ★ 2,482 updated 2026-10-06
.claude/commands/pentest-ai-agents-memory.mdWhat memory does
This command instructs Claude Code to document working progress inside .claude/PROJECT_MEMORY.md. The agent reads the existing file first. That keeps previous notes and project history intact.
The resulting summary captures modified features, bug fixes, technical decisions, and open TODO items. It also updates version history when applicable. Edits target .claude/PROJECT_MEMORY.md, so the environment must allow changes in the .claude directory.
What it helps with
- Log session progress and code changes automatically
- Record architectural decisions before ending the session
- Track pending tasks and bug fixes for upcoming runs
- Maintain project version notes across multiple sessions
Example prompts for the agent
- Update project memory with what was accomplished in this session
- /memory
- Document current fixes, decisions, and TODOs into .claude/PROJECT_MEMORY.md
How to install memory
Manually: put the files in place
.claude/commands/pentest-ai-agents-memory.mdThe built-in /memory overrides a file with the same name, so the file is renamed. Call it with /pentest-ai-agents-memory. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/memory.mdCall it with /prompts:memory. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/memory.prompt.mdManually: put the files in place
.gemini/commands/memory.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about memory
How to install memory in Claude Code?
Place the command file at .claude/commands/pentest-ai-agents-memory.md in your project repository.
What does the memory command do?
It reads .claude/PROJECT_MEMORY.md, appends a summary of changes, decisions, and remaining tasks from the current session, and saves the file.
Does the memory command overwrite existing project notes?
No. The prompt instructs the agent to read .claude/PROJECT_MEMORY.md first and preserve all existing content while adding new notes.
Source text
memory.md · MIT
{
"name": "memory",
"description": "Update the project memory with what was accomplished in this session",
"prompt": "Update the project memory file at .claude/PROJECT_MEMORY.md with a summary of everything that was done in this session. Include:\n1. What features were added or changed\n2. What bugs were fixed\n3. What decisions were made\n4. What is still TODO\n5. Update version history if applicable\n\nRead the current PROJECT_MEMORY.md first, then update it preserving all existing information while adding the new session's work."
}
© 0xSteph · MIT · 0xSteph/pentest-ai-agents
Similar slash commands
All slash commands for Agent setup: memory, context, orchestration →memory by other authors comes first.