Subconscious v1.5 — Bounded Self-Improving Agent

What It Is

A persistent, self-evolving bias layer that survives session resets. Alfred's "second brain" — quiet, bounded, and strictly governed. It does NOT make decisions. It shapes how Alfred approaches decisions.

Core principle: Every mutation is typed, bounded, and logged. Core identity is untouchable without manual override.

Architecture

CODEBLOCK0

Three layers:

• - core/ — Immutable identity (Alfred's nature, Edward's preferences). Manual-only.
• INLINECODE1 — Active learnings from experience. Governed promotion from pending.
• INLINECODE2 — Queue for new items. Bounded reinforcement before promotion eligibility.

Five bias types:

Lifecycle Commands

All commands run from scripts/ directory inside the skill:

CODEBLOCK1

Metabolism Cycles

Tick (every 5 min)

python3 subconscious_metabolism.py tick

• - Scans .learnings/ via learnings bridge → queues new items to pending
• Passive reinforcement: increments reinforcement count on pending items
• Skips already-reinforced items (prevents type corruption)
• Runs bounded maintenance: freshness decay, metrics, no structural changes

Rotate (hourly)

python3 subconscious_metabolism.py rotate --enable-promotion

• - Full maintenance: flush, decay, snapshot rotation
• Promotion gate (only with --enable-promotion):

• - Governance enforces typed mutation bounds on all items

Review (daily at 6am)

python3 subconscious_metabolism.py review

• - System health check
• Snapshot integrity
• Pending queue depth check
• Recommendations log

Learnings Bridge

The learnings bridge connects the self-improving-agent skill to the subconscious:

• - Scans .learnings/LEARNINGS.md, .learnings/ERRORS.md, INLINECODE16
• Tracks seen entries per file in INLINECODE17
• New entries → queued to pending.jsonl with type INLINECODE19
• Entries already reinforced in this session → skipped (idempotent)

Bridge to self-improving agent: The learnings bridge should be called from the metabolism tick so that new learnings flow into the subconscious every 5 minutes automatically.

Checking System Health

CODEBLOCK5

Expected output:
CODEBLOCK6

If Pending: 0/500 and Live: N — system is healthy, items promoting correctly.
If Status: blocked — resource limits hit, run rotate to compact.

Adding Items Manually

CODEBLOCK7

Key Files

For Claude Code Sessions

When Claude Code needs to assess or improve the subconscious system, use the claude-cx wrapper:

CODEBLOCK8

Cron Setup

After running install.sh, four cron jobs are active:

• - */5 * * * * — tick (light metabolism)
• INLINECODE39 — rotate (hourly, with promotion)
• INLINECODE40 — review (daily health check)
• INLINECODE41 — weekly benchmark (Monday 9am, compares to baseline)

Weekly Benchmark

Compares current state to the baseline snapshot captured at install time. Reports on:

• - Learnings volume change (LEARNINGS.md, ERRORS.md entries)
• New biases promoted to live
• Pending queue depth
• Error recurrence as a proxy for learning effectiveness

CODEBLOCK9

To capture a new baseline:
CODEBLOCK10

To override workspace location:
CODEBLOCK11