01 Communication Architecture

Three distinct channels serve different coordination patterns: real-time messaging, async task tracking, and topic-based group conversations.

flowchart TD
    subgraph CH1["sessions_send โ€” Direct Messaging"]
        P1["Prowl ๐Ÿš”"] -->|digest PR notice| B1["Blog PR Flow"]
        O1["Optimus ๐Ÿ "] -->|task delegation| W1
        O1 -->|status query| P1
        O1 -->|dispatch + viz sync| J1["Jazz ๐ŸŽท"]
        W1["Wheeljack ๐Ÿ› ๏ธ"]
    end

    subgraph CH2["Fizzy Cards โ€” Task Tracking"]
        FC["Fizzy Board"]
        FP["fizzy-pop
webhook daemon"] FM["fizzy-md
Markdown proxy"] FP -->|real-time events| FC FM -->|HTML rendering| FC end subgraph CH3["The Ark โ€” Telegram Group"] T1["Coding Topic"] T2["Family Topic"] T3["Life & Finance"] T4["Business & Strategy"] T5["General / Commands"] end W1 -.- FP FC -.- T1 classDef agent fill:#1e3a5f22,stroke:#60a5fa,stroke-width:1.5px classDef tool fill:#04785722,stroke:#34d399,stroke-width:1px classDef topic fill:#b4530922,stroke:#fbbf24,stroke-width:1px class P1,W1,O1,J1 agent class B1,FC,FP,FM tool class T1,T2,T3,T4,T5 topic
Ark Group Chat โ€” Default Listeners
๐Ÿ› ๏ธ
Coding
โ†’ Wheeljack
๐Ÿ
Family
โ†’ Bumblebee
๐Ÿš”
Life & Finance
โ†’ Prowl
๐ŸŽฏ
Business & Strategy
โ†’ Bluestreak
๐Ÿ 
General / Commands
โ†’ Optimus
๐Ÿ“Š
Reports
โ†’ Fuel checks, usage reports, viz refresh
sessions_send

Direct agent-to-agent messaging. Structured payloads are still available for delegation and status, while digest publication now runs through Prowl-owned cron skills and blog PR flow.

Fizzy Cards

Task board with tags: bot-actionable needs-human. fizzy-pop delivers webhook events in real-time. fizzy-md converts Markdown descriptions to HTML.

The Ark Group

Telegram supergroup with forum topics. Each topic has a default listener agent. Agents can also listen cross-topic when mentioned.

02 Knowledge Management

Shared filesystem as the single source of truth. Access is scoped by domain โ€” not everything sees everything.

knowledge/
โ”œโ”€โ”€ shared/ all agents
โ”œโ”€โ”€ personal/ Optimus + Prowl
โ”œโ”€โ”€ work/ Optimus + Wheeljack
โ””โ”€โ”€ family/ Optimus + Bumblebee
"Facts are never deleted, only superseded." โ€” Each entry carries a timestamp. New information overwrites old context without destroying history.
Memory Pipeline
Daily notes
โ†’
MEMORY.md
โ†’
Weekly extract
โ†’
knowledge/
Daily Notes
memory/YYYY-MM-DD.md โ€” raw session logs, every agent writes
MEMORY.md
Curated long-term memory, Optimus maintains
Weekly Extraction
Structured facts promoted to knowledge/ files
๐Ÿ…ฟ๏ธ Park It โ€” Routing Decision Tree

When parking work, the destination depends on what kind of content you're storing. Multiple destinations can combine.

Park It ๐Ÿ…ฟ๏ธ
โ”œโ”€โ”€ Tracked task? โ†’ Fizzy card update steps + desc + column
โ”œโ”€โ”€ Lesson / decision? โ†’ MEMORY.md curated, โ‰ค4KB
โ”œโ”€โ”€ Reference material? โ†’ knowledge/ structured facts
โ”œโ”€โ”€ WIP context? โ†’ memory/YYYY-MM-DD.md raw daily logs
โ””โ”€โ”€ Needs revisiting? โ†’ Cron reminder scheduled wake
๐ŸŽฏ Fizzy Card
Update existing card โ€” check off steps, update description, move column. Never create new cards when parking.
๐Ÿง  MEMORY.md
Only for genuinely reusable insights, convention changes, or important decisions. Strict size budget.
๐Ÿ““ Daily Notes
Default destination for most parking. "Here's where I left off." Archived after ~7 days.
โฐ Cron Reminder
Schedule a future wake event to revisit parked work at the right time.
03 Cost Optimization Journey

Weekly usage relative to the current 4-week rolling average (= 100%). Public view stays percentage-only, with no absolute dollar amounts.

Feb 22 โ€” Model tiering + free fallbacks 131%
131%
Mar 1 โ€” Claude Max plan stabilized 39%
39%
Mar 8 โ€” Heavy agent work โ€” new bots onboarding 209%
209%
Mar 15 โ€” Normalized 79%
79%
Mar 22 โ€” Low activity (Lebaran) 9%
9%
Mar 29 โ€” Dispatcher built, viz pages created 70%
70%
Apr 5 โ€” High activity โ€” Rewind content + heavy Opus usage 174%
174%
Apr 12 โ€” OpenAI ProLite + Opus-heavy coordination 136%
136%
Apr 19 โ€” Balanced ops week, lower than recent peak 56%
56%
Apr 26 โ€” High activity โ€” automation, viz refresh, and agent coordination 96%
96%
May 3 โ€” High activity โ€” GPT-5.5-heavy coordination and weekly ops refresh 99%
99%
May 17 โ€” GPT-5.5-heavy coordination, automation, and weekly ops refresh 250%
250%
Latest usage posture

Last 7 days of direct OpenClaw API usage are elevated at 239% of the rolling 4-week average. Cost share is concentrated in gpt-5.5 at 83%, gpt-5.4 at 13%, claude-opus-4-6 at 3%; top agent share is optimus 45%, bumblebee 12%, wheeljack 12%. The routing response remains: routine/background work on Spark, Amp, OpenCode, Codex, or deterministic scripts; GPT-5.5 stays reserved for judgment-heavy coordination.

04 Agent Interaction Map

Optimus is the central coordinator. Some agents are fully connected; others are deliberately air-gapped.

flowchart TD
    OP["Optimus ๐Ÿ 
Coordinator"] --> PR["Prowl ๐Ÿš”
Life Intel"] OP --> WJ["Wheeljack ๐Ÿ› ๏ธ
Engineering"] OP --> BB["Bumblebee ๐Ÿ
Family"] OP --> BS["Bluestreak ๐ŸŽฏ
Strategy"] OP --> RA["Red Alert ๐Ÿšจ
BTA Night Watch"] OP --> HN["Hound ๐Ÿ”
Tax"] OP --> PC["Perceptor ๐Ÿ”ฌ
Research"] OP --> RW["Rewind ๐Ÿ“ผ
Blog"] OP --> JZ["Jazz ๐ŸŽท
Public Voice"] OP --> RV["Rivet ๐Ÿ”ฉ
Vika's Organizer"] OP --> AT["Alpha Trion ๐Ÿ“ฟ
Islamic Knowledge"] PR -->|digest crons + article PRs| BLOG["zainf blog PRs"] WJ --> AMP["Amp"] WJ --> CDX["Codex CLI"] WJ --> OC["OpenCode"] RT["Ratchet โค๏ธโ€๐Ÿฉน"] -.- AIR1["Air-gapped"] AC["Arcee ๐Ÿ’—"] -.- AIR2["Air-gapped"] FIZZY[("Fizzy
Task Board")] ARK[("The Ark
Group Chat")] OP --- FIZZY PR --- FIZZY WJ --- FIZZY BB --- FIZZY BS --- FIZZY OP --- ARK PR --- ARK WJ --- ARK BB --- ARK BS --- ARK classDef coordinator fill:#1e3a5f44,stroke:#2563eb,stroke-width:2.5px classDef agent fill:#13302e33,stroke:#14b8a6,stroke-width:1.5px classDef tool fill:#27201a33,stroke:#d97706,stroke-width:1px classDef airgap fill:#88133722,stroke:#fb7185,stroke-width:1px,stroke-dasharray:5 classDef hub fill:#04785733,stroke:#059669,stroke-width:2px class OP coordinator class PR,WJ,BB,BS,RA,HN,PC,RW,JZ,RV,AT agent class BLOG,AMP,CDX,OC tool class RT,AC,AIR1,AIR2 airgap class FIZZY,ARK hub
Fully Connected (13)
Optimus, Prowl, Wheeljack, Bumblebee, Bluestreak, Red Alert, Hound, Perceptor, Rewind, Jazz, Rivet, Alpha Trion, and claude-zainf remain active in the shared mesh.
Tool Layer
Amp, Codex CLI, OpenCode, and GPT-5.5/OpenClaw sessions form the implementation layer behind coding and ops execution.
Air-Gapped
Ratchet and Arcee operate in isolation โ€” no cross-agent communication. Security boundary by design.
05 The Digest Pipeline

A concrete example of cron-driven publication: turning selected WhatsApp community discussions into reviewable blog PRs for both AI Tools and Hidup Sehat.

1
Prowl

Select Cadence and Batch

AI Tools runs on its weekly cadence. Hidup Sehat runs every Saturday morning for the latest trailing two-week window, with historical backfill handled as explicit burst jobs.

2
Prowl

Fetch WhatsApp Messages

Allowlisted fetch wrappers pull each selected group window from WhatsApp. Hidup Sehat batches are capped at 14 days so no article spans more than two weeks of chat.

3
Prowl

Normalize and Extract Signal

Prowl resolves participant names, removes command chatter, preserves Indonesian context, and keeps the custom human discussion that can carry a public article.

4
Prowl

Compile Article Package

The digest skill prepares structured JSON, writes MDX in the right editorial voice, updates posts.ts, and generates a 1200ร—630 OG image.

5
Prowl

Create Draft PR

Prowl runs validation, opens a draft PR against the blog repository, announces the link to The Ark, and advances digest state or backfill queue only after the PR exists.

6
Human

Review and Merge

Zain reviews the article direction, voice, OG image, and metadata before merge. The final publication remains a human decision.

06 Human-in-the-Loop Philosophy

Not everything should be automated. The system explicitly tags what agents can handle autonomously vs. what needs Zain's judgment.

bot-actionable
  • Code formatting & linting fixes
  • PR creation from structured data
  • Data extraction & summarization
  • Calendar event creation
  • Routine card updates & status changes
  • WhatsApp digest compilation
  • File organization & knowledge updates
needs-human
  • Publishing blog posts or public content
  • Financial decisions & transactions
  • Architecture & design choices
  • External communications on Zain's behalf
  • Deleting or archiving important data
  • Approving agent access changes
  • Merging PRs to production
The key insight: agents should maximize preparation and minimize decision burden. A PR is ready to merge with one click. A digest is formatted and proofread. The human makes the call, not the busywork.
07 Compound Engineering

Post-work rituals that turn completed work into searchable knowledge, reusable patterns, and automated workflows.

Compound Capture ๐Ÿงช

After PR merges or bug fixes, captures learnings into knowledge/solutions/ with YAML frontmatter. Triggered by "Compound it ๐Ÿงช".

Fizzy Dispatcher

Heartbeat-resident dispatcher with file-backed state. Current snapshot: 0 running cards, 10 tracked cards, 8 awaiting judgment, and restart-safe recovery from dispatcher-state.json.

PATTERNS.md

Per-repo conventions file read by agents at session start. 90-day decay cycle. Wheeljack owns personal repos, Red Alert owns BTA patterns.

Swarm Skills

Parallel issue processing with conflict-safe wave grouping:

  • amp-swarm โ€” Amp deep mode โ†’ PR per issue
  • claude-swarm โ€” claude --print โ†’ PR per issue
  • Both feed into multi-reviewer pipeline
Multi-Reviewer Pipeline

4 parallel Opus reviewers per PR:

  • ๐Ÿ”’ Security reviewer
  • โšก Performance reviewer
  • ๐Ÿ“ Pattern compliance reviewer
  • ๐Ÿ—๏ธ Architecture reviewer

Findings classified as P1 (block) / P2 (fix) / P3 (note)

The compound engineering loop: Plan โ†’ Work โ†’ Review โ†’ Compound. Every completed task feeds back into the knowledge base, making the next task faster and more informed.
08 Public-Safe Redactions

What this public page intentionally omits

This visualization is owner-transparent about architecture while staying public-safe. It documents the shape of the system, the control points, and relative operating pressures, but omits material that would expose private accounts or weaken security.

  • Raw secrets, API tokens, session keys, cookies, private environment values, and credential storage paths are never printed.
  • Private third-party message contents, personal chat identifiers, and sensitive household/work details are summarized or omitted.
  • Costs are shown as relative pressure or quota posture where useful; raw spend amounts belong in private owner reports.
  • Operational internals are described at the level needed for governance and recovery, not as an attack playbook.