Remember All Prompts Daily

Preserve conversation continuity across token compaction cycles by extracting and archiving all prompts with date-wise entries. Automatically triggers at 95% token usage (pre-compaction) and 1% (new sprint start) to export session history, then ingests archived summaries on session restart to restore context.

Security Scan

The skill's code and instructions match its stated purpose (archive and restore prompts) but it requires writing full conversation history to disk and relies on environment-specific commands/triggers, so review before use.

Purpose & Capability

The name/description (archive and reinstate prompts across token cycles) aligns with the included scripts (export_prompts.py, ingest_prompts.py, check_token_usage.py, setup_cron.py). No unrelated credentials, binaries, or install steps are requested.

Instruction Scope

Instructions explicitly read and append full prompts/responses to memory/remember-all-prompts-daily.md and then re-ingest them. That is functionally correct for the stated purpose but is a privacy-sensitive action (stores entire conversation text, potentially including secrets). The SKILL.md also references environment-specific commands (sessions_history(), session_status, clawdbot cron add) and modifying HEARTBEAT.md — these touch files/commands outside the skill folder and may not exist or may have broader side effects.

Install Mechanism

No install spec; this is instruction + script files only. Nothing is downloaded from external URLs and no archive extraction is specified.

Credentials

No environment variables or credentials are requested, which is appropriate. However, the skill writes full conversation history to disk — that is a legitimate need for the feature but increases risk of sensitive-data exposure if the host filesystem is not secured or backups are shared.

Persistence & Privilege

always is not set (so not force-installed), but disable-model-invocation is not set either, meaning the model could invoke these scripts automatically when token thresholds are reached. That behavior is consistent with the description but may surprise users who prefer explicit/manual dumps.

Assessment

This skill does what it says — it archives entire prompts/responses to a daily markdown file and can re-ingest them to restore context. Before installing: (1) review the four script files to confirm they do not transmit data off-host or run unexpected commands; (2) be aware that all conversation text (including any secrets) will be written to memory/remember-all-prompts-daily.md and possibly persisted in backups — secure that path or change storage behavior; (3) verify that the environment functions the skill expects (sessions_history(), session_status, clawdbot, HEARTBEAT.md) exist or adapt the scripts; (4) if you want manual control, consider setting disable-model-invocation or requiring explicit user triggers so the model cannot auto-run exports; (5) confirm daily rotation and retention policy meet your privacy/compliance needs.

This skill maintains conversation continuity across token budget cycles by automatically archiving your session history before compaction and restoring it when a new session begins.

How It Works

1. Extraction Trigger (95% Token Usage)

When token usage approaches 95%:

• Run export_prompts.py to extract current session history
• Format all prompts/responses with timestamps
• Append to memory/remember-all-prompts-daily.md with date-wise entry
• Marks the archive point so compaction can proceed

2. Fresh Session Trigger (1% Token Usage)

When a new session starts (fresh 1% token usage):

• Check if memory/remember-all-prompts-daily.md exists
• Read the most recent entry
• Ingest it as "past conversation summary" to restore context
• Continues naturally from where the previous session ended

3. Daily File Structure

# Remember All Prompts Daily

## [DATE: 2026-01-26]

### Session 1 (09:00 - 09:47)
[All prompts and responses from session]

### Session 2 (10:15 - 11:30)
[All prompts and responses from session]

Scripts

scripts/export_prompts.py

Extracts all prompts/responses from current session and archives them.

Usage:

python scripts/export_prompts.py

What it does:

• Uses sessions_history() to fetch all messages from current session
• Formats with timestamps and message IDs
• Appends to memory/remember-all-prompts-daily.md
• Includes metadata (token count, duration, etc.)

scripts/ingest_prompts.py

Reads the daily archive and injects it as context on session start.

Usage:

python scripts/ingest_prompts.py

What it does:

• Reads memory/remember-all-prompts-daily.md (if exists)
• Extracts most recent session
• Returns formatted summary for ingestion into new session

Integration

Heartbeat Check

Add to HEARTBEAT.md to monitor token usage:

Check token usage - if >95%, export session history

Cron Job (Optional)

For automatic triggers:

# Check token at regular intervals
clawdbot cron add --text "Check token usage and export if needed" --schedule "*/15 * * * *"

Example Flow

Session 1:

1. Chat normally
2. Token reaches 95%
3. export_prompts.py runs automatically
4. All prompts archived to daily file
5. Session compacts

Session 2 (New Sprint):

1. Fresh 1% token budget
2. ingest_prompts.py reads archive
3. "Here's what we discussed yesterday..."
4. Context restored, conversation continues seamlessly

Manual Usage

Export Right Now

python skills/remember-all-prompts-daily/scripts/export_prompts.py

View Today's Archive

cat memory/remember-all-prompts-daily.md | tail -100

Ingest Previous Session

python skills/remember-all-prompts-daily/scripts/ingest_prompts.py

Token Monitoring

Monitor token usage via:

session_status  # Shows current token usage %

When you see token usage approaching 95%, the skill can auto-trigger, or you can manually export.

Notes

• Runs only in main session (direct chat with Ateeb)
• Respects privacy — only stores your actual prompts and responses
• Daily file auto-rotates at midnight (one entry per date)
• Can be manually triggered anytime