Search Results

## §3 Proposed: `~/.claude/user.md` **Purpose:** Describe Alem Basic as a user of the John system. Loaded at session boot. Authoritative source for any agent needing to understand who it is serving and how. **Length target:** 60-80 lines. One page equivalent...

## §5 AI-Interview Template The AI interview is a live session (~20 minutes) where John asks Alem structured questions. Answers are recorded verbatim then edited into user.md and personality.md. Goal: avoid auto-write hallucination. John should not guess — Al...

## §6 Wiring After user.md and personality.md are created, `~/.claude/CLAUDE.md` must reference them in the Context Loading table so they are loaded at session boot. Patch to add to the `## Context Loading` table in `~/.claude/CLAUDE.md`: ```diff | Before....

## §3 — Feature Matrix (D1 / AC#1) Key: S=small (<8h), M=medium (<80h), L=large (>80h); EVIDENCE lines follow each cell. | Framework | storage_backend | embedding_model | extraction_method | recall_at_10 | latency_p50_ms | multi_user_isolation | oauth_compat...

## §4 — Cost Matrix Monthly (D2 / AC#2) Load assumptions per forged prompt D2: 200 queries/day × 30d = 6,000 queries/month; Stop-hook extraction: ~10 sessions/day × 30d = 300 extraction events. ### Scenario (a): $30 combined Pillar #9 + L3 (chip-huyen SC-2 i...

## §5 — Integration Effort Estimate (D3 / AC#3) | Framework | hours | dependencies | blocking_tasks | hooks_touched | agents_touched | settings_json_deltas | risk_factors | |-----------|-------|--------------|----------------|---------------|----------------|...

## §6 — Recommended Winner + Rationale (D4 / AC#4) **Pre-condition gate:** /tmp/forged-99124-evidence.jsonl contains 42 records (≥40 required). Verified: `wc -l /tmp/forged-99124-evidence.jsonl → 42` at 2026-05-04T21:20Z. ### winner: Mem0 self-hosted ### ru...

## §7 — Migration Plan (D5 / AC#5) Winner = Mem0 self-hosted. No migration away from existing deployment required. Plan = activation of Phase 2 items from stop-hook-l3-memory-spec.md. **LightRAG data export (for reference — required if future winner changes)...

## §8 — Pillar #9 Interplay + OAuth (D6 / AC#6) ### Topic 1 — Memory-layer location (laptop vs VM vs hybrid) **Decision:** Mem0 = laptop-only (ANVIL) for now. Qdrant port 6333 and Ollama port 11434 are both ANVIL-local. vm-alai-support (Pillar #9) does not h...

## §9 — Validation Harness — 20-Query Golden Set (D7 / AC#7) **Chip-huyen SC-3:** 20 queries from recall-eval-v2.sh lines 76-114 appear verbatim below. **Execution:** OUT OF SCOPE for MC #99124 — Phase 2 child MC. Scoring function fields per query: recall@10...

## §3 Proposed Convention ### 3.1 Root location All skill outputs, evidence artifacts, and forge deliverables write under: ``` ~/projects//// ``` Where: - `` — client slug (e.g., `bilko`, `drop`, `intesa`) or `alai` for internal ALAI work. - `` — one of: s...

## §4 Tool Support ### 4.1 `output-path.js` helper **Location:** `~/system/tools/output-path.js` **CLI interface:** ```bash node ~/system/tools/output-path.js resolve \ --client alai \ --skill task-postflight \ --mc 99292 ``` Returns: absolute path ...

## §5 Migration Phases Migration is additive. No existing file is moved. No existing convention is broken. Each phase adds structure; nothing removes it. ### Phase 1 — Week 1: Tool exists, new invocations opt in **Deliverable:** `~/system/tools/output-path....

## §6 Enforcement Three options, ranked by intrusiveness: ### Option A — Lint-on-mc-ready (least intrusive) [RECOMMENDED] A `pre-mc-ready` bash hook intercepts `mc.js ready ` calls. It reads the MC outcome/evidence field and checks whether any path referenc...

## §7 Per-Skill Examples ### 7.1 task-postflight **Current behavior:** Evidence written to `/tmp/postflight-/` (when it exists at all). Outcome is terminal output only. Brief (the AC list) exists only in the MC description, not alongside the output. **After...