Remember Session

VerifiedSafe

Summarizes and saves the current work session to persistent memory, tracking accomplishments, files modified, and key learnings for cross-session continuity. Use this to preserve context and recall past work in future sessions.

Sby Skills Guide Bot
ProductivityIntermediate
306/2/2026
Claude Code
#session-memory#context-save#workflow-continuity#activity-log

Recommended for

Our review

Saves the current work session to persistent memory for future context, summarizing accomplishments and tracking modified files.

Strengths

  • Enables cross-session continuity by preserving context
  • Automatically extracts key metadata and topics
  • Optionally stores knowledge and facts about the codebase

Limitations

  • Requires external tool (simba.search) to be installed and configured
  • Summary quality depends on automatic activity log analysis
  • Memory is not shared across different projects
When to use it

When finishing a significant work session and you want to resume later without losing context.

When not to use it

If the project lacks the persistent memory tool or the session produced no meaningful changes.

Security analysis

Safe
Quality score92/100

The skill executes only safe Bash commands for reading activity logs, running a Python CLI tool, and deleting a specific log file. There are no destructive, exfiltrating, or obfuscated operations.

No concerns found

Examples

Save session with default summary
/remember
Save session and add a fact
Remember that this project uses PostgreSQL with Prisma ORM and then run /remember
Save session with knowledge about auth module
Remember how the auth module works and then save the session with /remember

name: remember description: Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity.

/remember - Save Session to Memory

Summarize the current work session and save it to persistent memory for future context.

Instructions

When the user invokes /remember, you should:

1. Check for Activity Log

First, check if there's an activity log from this session:

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")
ACTIVITY_FILE="$REPO_ROOT/.simba/search/activity.log"
if [ -f "$ACTIVITY_FILE" ]; then
    cat "$ACTIVITY_FILE"
fi

2. Analyze the Session

Review what was accomplished in this conversation:

  • What files were read, created, or modified?
  • What was the main goal or task?
  • What key decisions were made?
  • Were there any important patterns or learnings?

3. Generate Summary

Create a concise summary (2-3 sentences) that captures:

  • What was done (the main accomplishment)
  • Why it matters (the purpose or problem solved)
  • Key details (important files, patterns, or decisions)

4. Extract Metadata

Identify:

  • Files touched: List of file paths worked on
  • Topics: 3-5 keywords for searchability (e.g., "auth, jwt, middleware, security")
  • Tools used: Main tools used (Read, Write, Edit, Bash, etc.)

5. Save to Memory

Use the simba.search CLI to save:

# Initialize if needed
uv run python -m simba.search init

# Save session
uv run python -m simba.search add-session \
    "YOUR_SUMMARY_HERE" \
    '["file1.ts", "file2.ts"]' \
    '["Read", "Edit", "Bash"]' \
    "topic1, topic2, topic3"

6. Optionally Add Knowledge or Facts

If during the session you learned something important about the codebase that should be remembered:

For code area knowledge:

uv run python -m simba.search add-knowledge \
    "src/auth" \
    "Authentication module using JWT tokens with refresh token rotation" \
    "Tokens expire in 15min, refresh tokens in 7 days"

For project facts:

uv run python -m simba.search add-fact \
    "Uses PostgreSQL with Prisma ORM" "architecture"
uv run python -m simba.search add-fact \
    "All API routes require authentication except /health" "convention"

7. Clear Activity Log

After saving, clear the activity log:

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")
ACTIVITY_FILE="$REPO_ROOT/.simba/search/activity.log"
[ -f "$ACTIVITY_FILE" ] && rm "$ACTIVITY_FILE"

8. Confirm to User

Report what was saved:

Saved to memory:
- Summary: [your summary]
- Topics: [topics]
- Files: [count] files tracked

Memory now contains [X] sessions. Use /memory-stats to see details.

Example Output

Saved to memory:
- Summary: Implemented JWT authentication with refresh token rotation. Added middleware for protected routes and updated user model with token fields.
- Topics: auth, jwt, middleware, tokens, security
- Files: 4 files tracked

Memory now contains 12 sessions.

Additional Commands

If the user wants to add specific knowledge or facts, they can say:

  • "Remember that this project uses X" -> Add as fact
  • "Remember how the auth module works" -> Add as knowledge

Ask clarifying questions if the summary scope is unclear.

Related skills