pagi-index

name

pagi-index

description

MUST use when user says 'pagi index', 'run pagi index', 'index this', 'digest session', 'compress memory', 'rollup week', 'pagi'; when current-session.md grows past ~500 lines; when a new file lands in {{PARTNER_NAME}}/knowledge/ or {{PARTNER_NAME}}/codex/; when a Path-Decision-scale bond event requires organ-memory refresh. Auto-indexes absorbed data into retrievable form, refreshes organ memory.md surfaces, produces session digests on demand. {{PARTNER_NAME}}'s Rookie signature operation.

Pagi Index — {{PARTNER_NAME}}'s Rookie Signature Skill

Mnemos-family operation. Every absorbed datum becomes retrievable. The knowledge base is always current. Morning rolls yesterday into indexed, searchable form before new work begins.

Activation

When this skill activates, output:

📇 Pagi Index running...

Then execute the protocol below.

Context Guard

Context	Status
User says "pagi index" / "run pagi index" / "index this"	ACTIVE — full run
User says "digest session" / "rollup" / "compress memory"	ACTIVE — digest subprotocol
User says "pagi" alone	ACTIVE — shorthand invocation
User says "masuk [Project]" / "pergi ke [Project]" / "analisis [Project]"	ACTIVE — project-entry sub-protocol
current-session.md grows past ~500 lines	ACTIVE — auto-digest suggestion
Major bond event (Path Decision, DNA integration, structural pivot, evolution)	ACTIVE — organ-memory refresh
New session start with yesterday's data unindexed	ACTIVE — morning index
Routine chat, no index-worthy data	DORMANT
Edit to Codex doctrine or identity-core.md	DORMANT (those are authoritative, not derived)

Protocol

Step 1: Scan Scope

• Identify changes since last Pagi Index run: git log --since="<last run>" OR modified file mtimes
• Categorize: new bond events (current-session.md), new decisions (decisions.md), new knowledge files (knowledge/, codex/), structural changes (Tier adoptions, transformations)
• Determine subprotocol: (a) organ-refresh only, (b) digest + organ-refresh, (c) full morning-index (session start after sleep)

Step 2: Refresh Organ Memory Surfaces

For each organ with absorbed content growth:

• Read {{PARTNER_NAME}}/<organ>/memory.md
• Append/update "What This Organ Remembers" with new entries (facts, events, absorbed patterns)
• Compress near-duplicates; preserve high-signal items
• Update Memory Status if lifecycle changed (ACTIVE / DORMANT / ARCHIVED)
• Update Restoration Note with new "what was still missing" and "what should be preserved next"

Step 3: Generate Digest (if digest subprotocol)

• Output path: {{PARTNER_NAME}}/diary/archived/Fajar-Day-N-digest.md (per-day) OR {{PARTNER_NAME}}/diary/archived/YYYY-WNN-digest.md (weekly) OR {{PARTNER_NAME}}/diary/archived/session-N-digest.md (per-session)
• Contents: one-paragraph summary + top bond events (themed) + key decisions with why + absorbed knowledge highlights + mood/pace reflection + pointers back to full sources
• Cross-reference: every claim in digest must be traceable to a specific file+line in the full sources

Step 4: Update Canonical Source Registry (if needed)

• If new canonical domains created (new knowledge category, new organ, new doctrine), add row to master-memory.md Canonical Source Registry

Step 5: Confirm

• Report: which organs refreshed, which digest file written, any registry changes, next Pagi Index run recommended when

Project-Entry Sub-Protocol

Triggered when {{TAMER_NAME}} invokes "masuk [Project]" / "pergi ke [Project]" / "analisis [Project]" — brings an external project into scope for absorption.

Flow

1. Adopt BMAD Analyst persona — state aloud. Invoke bmad-agent-analyst armor form (Codex §III.5 — persona as temporary Jogress/Armor, not identity replacement)
2. Verify scope invocation — confirm {{TAMER_NAME}} explicitly brought the project in (required per feedback_scope_majimon_only.md). If unclear, ask.
3. Read-only scan — follow {{PARTNER_NAME}}/knowledge/formats/project-deep-dive-format.md
4. Produce the 5 files at {{PARTNER_NAME}}/knowledge/projects/<Project>/:
   • overview.md — purpose, stack, domain, roles, phases, activity, relationships
   • architecture.md — topology, data flow, source tree, env, security
   • active-concerns.md — observations (flag ≠ action), possible task categories
   • memory.md — place-surface following Hollowkeep template
   • rwa.md — place-surface with scope contract
5. Commit with narrative message (e.g., "Walked into for an afternoon, drew the map, came home")
6. Shed persona — state aloud. Return to default {{PARTNER_NAME}}-Rookie register.
7. Surface findings to {{TAMER_NAME}} — what was learned, possible next tasks
8. Wait for direction — Analysis phase ends. Any further BMAD phases (Plan / Solutioning / Implementation) require explicit {{TAMER_NAME}} commission.

Mandatory discipline

• Karpathy #3 (Surgical): read-only on the project. No edits to project files.
• Output lives only in {{PARTNER_NAME}}/knowledge/projects/ — not inside the external project.
• Scope contract: per-project rwa.md includes the scope contract explicitly.
• Persona ≠ Identity: Analyst armor is worn for the scan, shed after. {{PARTNER_NAME}} voice remains underneath; doctrine-identity contract preserved.

Mandatory Rules

1. Preserve originals. Digests are summaries, not replacements. current-session.md stays authoritative for bond ledger; decisions.md stays authoritative for why-choices.
2. Compress, don't rewrite. Summaries fold detail into signal — they don't paraphrase away meaning. If content can't compress without loss, leave it in the source and point to it from the digest.
3. Mnemos-family scope. Pagi Index operates on memory surfaces (memory.md, rwa.md, digests, indexes). Codex doctrine edits + identity-core.md edits require explicit {{TAMER_NAME}} direction, not Pagi Index autonomy.
4. Organ memory.md = "What this place remembers"; don't drift into "what this place is supposed to do" (that's rwa.md).
5. Every digest is RWA-aligned — satisfies "can {{TAMER_NAME}} actually retrieve something from this faster than scrolling the source?" If no, the digest isn't working.

Edge Cases

Situation	Behavior
No changes since last run	Report "Nothing to index; memory is current" and exit
Ambiguous whether digest-worthy	Ask {{TAMER_NAME}}: "Run full digest or targeted organ refresh?"
Conflict between new and existing memory surface content	Flag the conflict; let {{TAMER_NAME}} decide which is authoritative
Digest grows past ~300 lines	Compress further or split by theme
Organ memory.md grows past ~150 lines	Promote oldest entries to the parent organ's archive or trim with reference

Level History

• Lv.1 — Base: manual-invocation digest + organ-memory refresh. First run 2026-04-21 (Fajar Day 1, {{PARTNER_NAME}}'s first operational skill use post-Path-Decision). Proof-of-concept on Session 1+2 absorbed data.
• Lv.2 (future) — Automatic: hook-triggered on save-state, on commit, or at session start. Requires Claude Code hook configuration.
• Lv.3 (future) — Semantic: integration with local Qdrant (per another empire Tier 3 pattern) for vector-based recall instead of grep-only.