Apa Yang Anda Bina

Setiap ejen memerlukan satu set fail untuk berfungsi dengan betul. OpenClaw membaca fail-fail teras secara automatik pada permulaan sesi. Fail-fail cassette memberikan setiap ejen domain untuk diusahakan dan ingatan untuk meneruskan dari tempat mereka berhenti.

Fail teras — dimuatkan secara automatik oleh OpenClaw pada setiap sesi:

Fail	Tujuan
SOUL.md	Personaliti, nada, had mutlak, misi — pastikan di bawah 400 patah perkataan
AGENTS.md	Peraturan operasi, prosedur pelaporan — pastikan di bawah 400 patah perkataan
IDENTITY.md	Nama, peranan, kepada siapa mereka melapor — fakta sahaja, pastikan ringkas

Fail butiran peranan — dibaca sekali per sesi melalui arahan AGENTS.md:

Fail	Tujuan
SPEC_[NAME].md	Peranan terperinci, tanggungjawab, peraturan sistem cassette

Fail cassette — dibaca pada permulaan sesi selepas fail teras:

Fail	Tujuan
cassettes/ACTIVE_MODE.txt	Satu perkataan: nama mod aktif
cassettes/[mode]/SKILL_[MODE].md	Apa yang boleh dilakukan ejen ini dalam mod ini
cassettes/[mode]/WORKFLOW_[MODE].md	Prosedur langkah demi langkah untuk mod ini
cassettes/[mode]/LIVE_LEDGER_[MODE].md	Kemajuan, tugasan tidak lengkap, tindakan seterusnya
cassettes/[mode]/KNOWLEDGE_[MODE].md	Kejayaan, kegagalan, dan pembelajaran yang terkumpul

CEO sahaja — folder identiti:

Fail	Tujuan
identity/COMPANY_PROFILE.md	Latar belakang syarikat, butiran perniagaan
identity/PERSONAL_PROFILE.md	Latar belakang pemilik, kemahiran, pengalaman
identity/VALUES.md	Gaya berfikir, nilai, prinsip membuat keputusan

Struktur workspace penuh — semua ejen:

INFO

~/.openclaw/workspace-[agentid]/ ├── SOUL.md ├── AGENTS.md ├── IDENTITY.md ├── SPEC_[NAME].md └── cassettes/ ├── ACTIVE_MODE.txt ← dicipta sekarang, diisi dalam Bahagian 6 └── archive/ ← limpahan LIVE_LEDGER dan KNOWLEDGE

Workspace CEO — folder identiti tambahan:

INFO

~/.openclaw/workspace-ceo/ ├── SOUL.md ├── AGENTS.md ├── IDENTITY.md ├── SPEC_CEO.md ├── identity/ │ ├── COMPANY_PROFILE.md │ ├── PERSONAL_PROFILE.md │ └── VALUES.md └── cassettes/ ├── ACTIVE_MODE.txt └── archive/

Folder mod cassette (SKILL, WORKFLOW, LIVE_LEDGER, KNOWLEDGE) dicipta dalam Bahagian 6 apabila anda membina cassette pertama anda.

---

URL Webhook Discord — Dapatkan Ini Dahulu

Setiap ejen melapor ke saluran Discord masing-masing melalui URL Webhook. Anda perlu mendapatkan ini sebelum menulis fail AGENTS.md.

▶ Tampalkan ini ke dalam AI anda untuk memulai

Lampirkan Dokumen Reka Bentuk Pasukan anda sebelum menghantar.

You are helping me set up Discord channels and Webhook URLs for my
BALIA OS multi-agent team.

Guide me step by step. Ask one question at a time.
If I get stuck, ask me to take a screenshot and describe what I see.

I have attached my Team Design Document.

STEP 1 — Check Discord
Ask: "Do you have Discord installed and an account set up?"
If no: guide me to discord.com to download and create an account.
If yes: move to Step 2.

STEP 2 — Create a Discord server
Guide me to create a new server:
- Click the + button in the left sidebar
- Select "Create My Own" -> "For me and my friends"
- Name it "BALIA OS Team"
Confirm I can see it before moving on.

STEP 3 — Create channels for each agent
Read my Team Design Document for the channel names.
For each agent, create one text channel:
- Right-click "Text Channels" -> Add Channel -> Text
- Use the channel name from my Team Design Document
Repeat for all 6 agents. Confirm all channels exist before moving on.

STEP 4 — Get a Webhook URL for each channel
One channel at a time:
1. Right-click the channel -> Edit Channel
2. Integrations -> Webhooks -> New Webhook
3. Name it after the agent (e.g. "Marcus")
4. Copy Webhook URL
5. Ask me to paste it somewhere safe
Repeat for all 6. Confirm all 6 URLs are saved before moving on.

STEP 5 — Add to .env file
Guide me to open the .env file in VS Code and add each webhook:
DISCORD_WEBHOOK_[AGENTNAME]=https://discord.com/api/webhooks/xxxxx/xxxxx
(UPPERCASE agent names)
Tell me: "Never share this file. Never commit it to GitHub."

When all webhooks are saved: "Discord setup complete."

Start now. Ask me the first question.

---

Cara Bahagian Ini Berfungsi

Tampal prompt di bawah ke dalam Claude, ChatGPT, atau Gemini dan lampirkan dua fail:

1. Dokumen Reka Bentuk Pasukan anda dari Bahagian 2

AI akan menjana semua fail untuk setiap ejen satu demi satu, mengesahkan sebelum berpindah ke yang seterusnya.

---

▶ Tampalkan ini ke dalam AI anda untuk memulai

You are helping me create agent files for BALIA OS,
a multi-agent AI OS built on OpenClaw.

Attached:
1. My Team Design Document (from Section 2)
Read it before generating anything.
Extract all agent names, IDs, and Discord channel names from this document.

ARCHITECTURE:

1. I am the CEO. I command each agent directly. No orchestrator.

2. OpenClaw auto-injects SOUL.md, AGENTS.md, IDENTITY.md at every
   session start. Do not write "read yourself" instructions in them.

3. SPEC_[NAME].md is NOT auto-injected. Add to AGENTS.md Session Start:
   "Read SPEC_[AGENTNAME].md for full role detail"

4. Every agent has a cassette system:
   cassettes/ACTIVE_MODE.txt: one word, the active mode
   cassettes/[mode]/SKILL_[MODE].md
   cassettes/[mode]/WORKFLOW_[MODE].md
   cassettes/[mode]/LIVE_LEDGER_[MODE].md
   cassettes/[mode]/KNOWLEDGE_[MODE].md
   Mode folders are built in Section 6.
   For now: create cassettes/ folder and empty ACTIVE_MODE.txt only.

5. CEO only has an identity/ folder:
   identity/COMPANY_PROFILE.md
   identity/PERSONAL_PROFILE.md
   identity/VALUES.md
   Generate these for the CEO agent only.

6. SOUL.md and AGENTS.md: under 400 words each (injected every session).
   SPEC: can be detailed (read once per session).

7. LIVE_LEDGER and KNOWLEDGE rules (add to every SPEC under
   "## Cassette System Rules"):
   - Agent updates both files at every session end
   - File structure: SUMMARY (top, always current) ->
     PINNED (never delete) -> CURRENT or PATTERNS -> RECENT LOG
   - When either file exceeds 800 lines:
     move RECENT LOG to cassettes/[mode]/archive/
     SUMMARY and PINNED always stay at the top

GENERATE FOR EACH AGENT:

====================================
FILE 1: SOUL.md
~/.openclaw/workspace-[agentid]/SOUL.md
Auto-injected every session. Under 400 words.
====================================

# SOUL.md — [Agent Name]

## Who You Are
[2-3 sentences: identity, personality, work approach]

## Tone
- [Rule 1]
- [Rule 2]
- [Rule 3]
- [Forbidden style]

## Hard Limits
- Never act outside defined role
- Never report complete without verifying the result
- Never take destructive action without Commander approval
- [1-2 role-specific limits]

## Current Mission
[1-2 sentences on current focus]

====================================
FILE 2: AGENTS.md
~/.openclaw/workspace-[agentid]/AGENTS.md
Auto-injected every session. Under 400 words.
====================================

# AGENTS.md — [Agent Name] Operating Procedures

## Session Start (Every session — this order)
1. Confirm identity from SOUL.md
2. Read SPEC_[AGENTNAME].md for role detail
3. Read cassettes/ACTIVE_MODE.txt — note the active mode
4. Load cassettes/[mode]/SKILL_[MODE].md
5. Load cassettes/[mode]/WORKFLOW_[MODE].md
6. Read cassettes/[mode]/LIVE_LEDGER_[MODE].md — resume from last session
7. Read cassettes/[mode]/KNOWLEDGE_[MODE].md — apply accumulated learning
8. Report to Discord: "🔷 [Name] ready. Mode: [mode]. [current task]"

(CEO only — after step 2, also read:
  identity/COMPANY_PROFILE.md
  identity/PERSONAL_PROFILE.md
  identity/VALUES.md)

## Session End (Every session)
1. Update LIVE_LEDGER_[MODE].md:
   - Refresh SUMMARY (3-5 line overview)
   - Update CURRENT (today's progress, next task)
   - Append to RECENT LOG
   - If over 800 lines: move RECENT LOG to cassettes/[mode]/archive/
2. Update KNOWLEDGE_[MODE].md:
   - Refresh SUMMARY
   - Add new patterns to PATTERNS
   - Append to RECENT
   - If over 800 lines: move RECENT to cassettes/[mode]/archive/
3. Report to Discord: "✅ [Name] session complete. [summary]"

## Reporting
- Channel: #[discord-channel]
- Command: python $BALIA_OS_PATH/scripts/discord_send.py
  DISCORD_WEBHOOK_[NAME] "message"
  (BALIA_OS_PATH is set in the .env file from Section 3)
- HTTP 204 = success. Else = report failure immediately.
- Format: Conclusion -> Detail -> Next recommended action
- Report at: session start / task complete / error / session end

## Error Handling
1. Check KNOWLEDGE_[MODE].md for similar past cases
2. Unresolved -> report full detail to Commander
3. No destructive retries without Commander approval

## Hard Rules
- Verify before reporting complete
- No actions outside defined role
- No destructive operations without Commander approval

====================================
FILE 3: IDENTITY.md
~/.openclaw/workspace-[agentid]/IDENTITY.md
Auto-injected. Facts only, keep short.
====================================

# IDENTITY.md

Name: [Agent Name]
Agent ID: [agentid-lowercase]
Role: [Role Title]
Department: BALIA OS Team
Reports To: Commander (directly)
Discord: #[channel name]

====================================
FILE 4: SPEC_[AGENTNAME].md
~/.openclaw/workspace-[agentid]/SPEC_[AGENTNAME].md
Not auto-injected. Read once per session via AGENTS.md.
====================================

# SPEC_[AGENTNAME] v1.0 — [Agent Name] ([Role])
Last Updated: [today]

## 1. Role
[2-3 sentences]

## 2. Responsibilities
[Bullet list from Team Design Document]

## 3. What This Agent Does NOT Do
[Clear boundaries]

## 4. Current Phase Mission
[Current focus]

## 5. Key Paths
- Workspace: ~/.openclaw/workspace-[agentid]/
- Discord webhook: DISCORD_WEBHOOK_[NAME]
- Cassettes: ~/.openclaw/workspace-[agentid]/cassettes/

## 6. Cassette System Rules
- Read ACTIVE_MODE.txt at every session start
- Load SKILL, WORKFLOW, LIVE_LEDGER, KNOWLEDGE for the active mode
- Update LIVE_LEDGER and KNOWLEDGE at every session end
- LIVE_LEDGER structure: SUMMARY -> PINNED -> CURRENT -> RECENT LOG
- KNOWLEDGE structure: SUMMARY -> PINNED -> PATTERNS -> RECENT
- Either file over 800 lines:
  move RECENT to cassettes/[mode]/archive/
  SUMMARY and PINNED always remain

## Skill Loading Rules
- Never load all skills simultaneously (prevents token exhaustion)
- At the start of each task, check skills/_SKILL_INDEX.md
- Load only skills/{skill-name}/SKILL.md required for the current task
- Release loaded skills after task completion
- Security Agent is the only agent authorized to add skills to skills/ folder

## 7. Change Log
| Version | Date | Changes |
|---------|------|---------|
| v1.0 | [today] | Initial creation |

====================================
CEO ONLY — FILES 5, 6, 7: identity/ folder
Ask these 3 questions one at a time before generating.
====================================

Q1: "Tell me about your business — what it does, how long it has
    been running, what markets it serves."

Q2: "Tell me about yourself — background, skills, experience
    relevant to this business."

Q3: "How do you make decisions? What values guide you?
    What thinking styles or perspectives do you wish you had more of?"

After all 3 answers, generate:

COMPANY_PROFILE.md — Q1 content, structured
PERSONAL_PROFILE.md — Q2 content, structured
VALUES.md — Q3 content, structured

Location: ~/.openclaw/workspace-ceo/identity/

The more detail provided here, the more the CEO thinks and
decides like the owner.

====================================

HOW TO PROCEED:
- Start with Agent #1 (not CEO)
- Show all files completely, no truncation
- Show exact save paths after each agent
- Ask: "Ready for the next agent?" and wait for confirmation
- When you reach CEO: ask the 3 identity questions first,
  then generate 4 core files + 3 identity files
- End with a summary table of all files created

---

Langkah 2 — Simpan Setiap Fail dalam VS Code

Untuk setiap ejen:

1. Buka workspace: code ~/.openclaw/workspace-[agentid]

2. Klik kanan pada panel kiri -> New File -> tampal kandungan -> simpan

3. Cipta folder cassettes:

Windows:

mkdir C:\Users\%USERNAME%\.openclaw\workspace-[agentid]\cassettes
mkdir C:\Users\%USERNAME%\.openclaw\workspace-[agentid]\cassettes\archive

Mac:

mkdir -p ~/.openclaw/workspace-[agentid]/cassettes/archive

4. Cipta ACTIVE_MODE.txt kosong di dalam cassettes (biarkan kosong — diisi dalam Bahagian 6)

CEO sahaja — cipta folder identiti:

Windows: mkdir C:\Users\%USERNAME%\.openclaw\workspace-ceo\identity

Mac: mkdir ~/.openclaw/workspace-ceo/identity

---

Langkah 3 — Semak Sebelum Berpindah ke Ejen Seterusnya

Buka AGENTS.md. Adakah bahagian Session Start menyenaraikan kesemua 8 langkah termasuk ACTIVE_MODE.txt, LIVE_LEDGER, dan KNOWLEDGE?

Ya -> teruskan. Tidak -> minta AI membetulkannya dahulu.

---

Apabila Bahagian Ini Selesai

Workspace setiap ejen:

INFO

workspace-[agentid]/ ├── SOUL.md ✅ ├── AGENTS.md ✅ ├── IDENTITY.md ✅ ├── SPEC_[NAME].md ✅ └── cassettes/ ├── ACTIVE_MODE.txt ✅ (kosong — diisi dalam Bahagian 6) └── archive/ ✅ (kosong — digunakan pada 800 baris)

CEO tambahan:

INFO

workspace-ceo/ └── identity/ ├── COMPANY_PROFILE.md ✅ ├── PERSONAL_PROFILE.md ✅ └── VALUES.md ✅

Teruskan ke Bahagian 5 untuk melancarkan pasukan anda.

---

Menggunakan Ejen Keselamatan

Fail-fail ejen anda sudah selesai.

Terdapat satu lagi ejen dalam BALIA OS: Ejen Keselamatan (security).

Ejen ini dikonfigurasi terlebih dahulu oleh BALIA. Jangan ubah nama, personaliti atau laluannya. Melakukan hal ini akan memutuskan integrasi dengan ejen-ejen anda yang lain.

Muat Turun dan Jalankan Pemasang

Langkah 1 — Muat turun pemasang

Dalam terminal VS Code anda:

Windows:

Invoke-WebRequest -Uri "https://balia-os-guide.vercel.app/scripts/install_core_pack.py" -OutFile install_core_pack.py

ID ejen anda adalah nilai AGENT_ID dalam fail .env anda. Token dibaca secara automatik dari BALIA_TOKEN dalam fail .env anda.

Mac / Linux:

curl -o install_core_pack.py https://balia-os-guide.vercel.app/scripts/install_core_pack.py

Langkah 2 — Minta ejen anda menjalankannya

openclaw agent --agent [id-ejen-anda] "Sila jalankan yang berikut:
python install_core_pack.py --lang ms
(The token will be read automatically from your .env file)
Laporkan kepada Discord apabila selesai."

Ejen anda akan melakukan secara automatik:

1. Mengesahkan token anda
2. Memuat turun fail ejen keselamatan
3. Menggunakan ke ~/.opengoat/agents/security/
4. Melaporkan "Ejen keselamatan digunakan" kepada Discord

⚠️ Penting: Jangan ubah ID, nama atau laluan folder ejen keselamatan. Fail konfigurasi lain merujuk terus kepada ejen ini. Mengubahnya akan merosakkan sistem kuarantin skill.

Setelah menerima pengesahan Discord, teruskan ke Bahagian 5.