این پرامپت رزومه شما را در برابر هوش مصنوعی فیلترکننده‌ی کارفرما قرار می‌دهد تا قبل از اپلای، نقاط کور رزومه‌تان را شناسایی و اصلاح کنید.

کارفرمای خارجی نمی‌خواهد بداند شغل شما چه بود؛ می‌خواهد بداند چه تاثیری گذاشتید. این پرامپت جملات بی‌روح رزومه را به موتور تولید ارزش تبدیل می‌کند.

بخش درباره من (About) در لینکدین، بیانیه شخصی شماست. این بخش نباید تکرار رزومه باشد، بلکه باید داستان حرفه‌ای شما را روایت کند.

در استخدام‌های بین‌المللی، مصاحبه‌ها رفتاری هستند؛ یعنی کارفرما می‌خواهد بداند شما در شرایط بحرانی گذشته چه کرده‌اید. چارچوب استار (وضعیت، وظیفه، اقدام، نتیجه) استاندارد طلایی پاسخ‌دهی به این سوالات است.

ارسال یک ایمیل پیگیریِ کلیشه‌ای هیچ اثری ندارد. ایمیل موفق ایمیلی است که یک قلاب ذهنی از گفتگوی واقعی شما در مصاحبه را زنده کند.

125 صفحه آموزش کاربردی + بیش از 50 پرامپت کاملاً آماده برای موقعیت‌های واقعی شغلی، تجاری و اتوماسیون دیاسپورا.

میانگین تعداد اپلای فعال برای رسیدن به اولین دعوت به مصاحبه در کشورهای توسعه‌یافته (اروپا، کانادا و آمریکا) حداقل ۲۰۰ اپلای فعال است.

۱۷۵ صفحه سناریوهای واقعی، کدهای آماده برای خط فرمان و نقشه راه تسلط بر اتوماسیون در سال ۲۰۲۶.

🚨 بزرگ‌ترین اشتباه در کار با کلاود (Claude): ۹۹ درصد مردم با کلاود به روش «سیستم ۱» کار می‌کنند! یک پرامپت سریع می‌دهند، کلاود هم یک پاسخ سریع، زیبا اما سطحی (و گاهی فیک) تحویل می‌دهد. این چت‌باکس‌ها جوری طراحی شده‌اند که با نهایتِ سرعت به شما پاسخِ بله‌قربان‌گویانه بدهند. این یعنی اسباب‌بازی، نه سیستم‌سازی!

نقش تو: معمار ارشد سیستم و منتقد بی‌رحم (System 2 Validator)

مرحله ۱: ابتدا این کار را با نهایتِ خلاقیت انجام بده: [توضیح کار یا پروژه شما]
مرحله ۲: حالا از قالب خودت خارج شو. فرض کن تو یک ممیز و منتقد به شدت سخت‌گیر هستی. خروجی مرحله اول خودت را نقد کن: چه فرضیات اشتباهی داشتی؟ کجای آمارها فیک یا ضعیف است؟ چه ریسک‌های مالی یا عملیاتی در آن وجود دارد؟
مرحله ۳: با اعمال تمام نقدهای مرحله دوم، نسخه نهایی، مستدل و بدون خطای کار را بازنویسی کن.

💡 چرا این روش بی‌نظیر است؟ خروجی این فرآیند یک گزارش متنی ساده نیست؛ بلکه یک ساختار پوشه‌بندی‌شده و زنده در سیستم شماست که ارتباطات بین افراد، پروژه‌ها، تصمیمات و اسناد فنی را به صورت خودکار فرمت‌دهی و لینک‌سازی می‌کند.

/goal Build a mature, source-backed Obsidian vault brain.

Primary Objective:
Create a local Obsidian-compatible vault that functions as a durable context layer for LLMs and agents. The output must be a working vault folder, not merely a report. The vault must be source-backed, resumable, validated by scripts, and organized around canonical knowledge rather than raw dumps.

Before doing substantive work, confirm:
1. The current working directory.
2. The intended output root directory.
3. The available source locations and connectors.
4. The connected account/workspace/organization for every external connector.

If no output root is provided, create the compiled vault under the current working directory as:
Compiled-Vaults/compiled-vault-brain-YYYY-MM-DD/

Do not write the final vault to an ambiguous location.

Core Memory Architecture:
The vault must distinguish between declarative memory, procedural memory, source traces, context packs, and runtime tools/connectors.

Required First Phase: Orientation
Do not author the final vault immediately. First inspect available vaults, notes, documents, repos, generated examples, and connected tools.

Produce: Reports/ORIENTATION-REPORT.md

This report must include confirmed working directory, output path, source inventory, connector inventory, account/workspace verification results, initial high-signal entities, proposed ingestion plan, and blockers.

Hard Checkpoint 1:
After creating ORIENTATION-REPORT.md, pause and ask the user whether to proceed. Do not begin broad ingestion until the user approves.

Connector Verification Gate:
Before ingesting from any external connector, retrieve and document the actual connected account/workspace/organization for each connector and record it in SOURCE-MANIFEST.md.

If a connector is attached to the wrong account, mark it as blocked. Never perform any external actions without explicit user approval.

Required State and Resumption Files:
Create and maintain INGESTION-LOG.md and state.json so the process is fully resumable.

Required Compiler Process:
Use this repeatable process: parse → thread/group → classify → extract → canonicalize → rehydrate provenance → author → validate links → critic/audit

For large passes, use lighter models for early stages and the strongest model for synthesis and review.

Required Deterministic Machinery:
Create a _tools/ folder inside the vault with validation scripts for wikilinks, paths, secrets, source references, and required artifacts. Record results in VALIDATION-REPORT.md.

Redaction Policy:
Never copy secrets, API keys, tokens, or credentials into the vault. Prefer summaries and clear provenance.

Required Ingestion Plan:
- Ingest existing useful Markdown notes (prioritize people, projects, decisions, procedures, etc.).
- For email: Start with a small smoke test, then do broader passes only after user approval.

Hard Checkpoint 2:
After the initial smoke pass, show sample notes and ask for approval before continuing.

Required Vault Structure:
Include these folders: People/, Companies/, Projects/, Decisions/, Procedures/, Context Packs/, Sources/, _tools/, plus the required manifest and audit files.

Note Format:
Use clean Obsidian Markdown with YAML frontmatter, wikilinks, provenance, and clear structure. Do not invent facts.

Validation Hard Gates:
The vault is only complete when there are zero broken links, zero placeholder references, zero copied secrets, every note has provenance, and all validation scripts pass.

Execution Rules:
Work in phases, always resume by reading the log and state files first. Never make destructive changes or external writes without approval. Pause and ask the user before any broad or sensitive ingestion.

Quality Bar:
The final vault should be a structured, source-backed operating memory — not a raw data dump. It must help future agents clearly understand the user, their work, relationships, decisions, and procedures.

Completion Rule:
Do not mark the goal complete until the vault exists, all validations pass, and the required audit and manifest files confirm every requirement is satisfied.

💰 پتانسیل درآمدزایی این ورک‌فلو: ارزش واقعی این سیستم در مهندسی کانتکست (Context Engineering) است. شما می‌توانید همین فرآیند ساخت مغز دوم و سازماندهی اسناد را به عنوان یک سرویس گران‌قیمت به شرکت‌ها و کسب‌وکارهای کوچک ارائه دهید و برای پیاده‌سازی هر پروژه، مبالغی بالای ۵۰۰۰ دلار دریافت کنید.

🚀 مسیر دریافت هدایا بسیار ساده است: ۱. ایمیل خود را در کادر صفحه اول وب‌سایت ثبت کنید. ۲. بلافاصله لینک ورود مستقیم به کانال خصوصی تلگرام برای شما باز خواهد شد. ۳. هم‌زمان یک ایمیل حاوی لینک دانلود مستقیم هر ۴ کتابچه برای شما ارسال می‌شود. ⚠️ نکته مهم: حتماً پوشه Promotions و حتی Spam ایمیل خود را چک کنید تا فایل‌ها را از دست ندهید.

💡 چرا این روش بی‌نظیر است؟ خروجی این فرآیند یک گزارش متنی ساده نیست؛ بلکه یک ساختار پوشه‌بندی‌شده و زنده در سیستم شماست که ارتباطات بین افراد، پروژه‌ها، تصمیمات و اسناد فنی را به صورت خودکار فرمت‌دهی و لینک‌سازی می‌کند.

/goal Build a mature, source-backed Obsidian vault brain.

Primary Objective:
Create a local Obsidian-compatible vault that functions as a durable context layer for LLMs and agents. The output must be a working vault folder, not merely a report. The vault must be source-backed, resumable, validated by scripts, and organized around canonical knowledge rather than raw dumps.

Before doing substantive work, confirm:
1. The current working directory.
2. The intended output root directory.
3. The available source locations and connectors.
4. The connected account/workspace/organization for every external connector.

If no output root is provided, create the compiled vault under the current working directory as:
Compiled-Vaults/compiled-vault-brain-YYYY-MM-DD/

Do not write the final vault to an ambiguous location.

Core Memory Architecture:
The vault must distinguish between declarative memory, procedural memory, source traces, context packs, and runtime tools/connectors.

Required First Phase: Orientation
Do not author the final vault immediately. First inspect available vaults, notes, documents, repos, generated examples, and connected tools.

Produce: Reports/ORIENTATION-REPORT.md

This report must include confirmed working directory, output path, source inventory, connector inventory, account/workspace verification results, initial high-signal entities, proposed ingestion plan, and blockers.

Hard Checkpoint 1:
After creating ORIENTATION-REPORT.md, pause and ask the user whether to proceed. Do not begin broad ingestion until the user approves.

Connector Verification Gate:
Before ingesting from any external connector, retrieve and document the actual connected account/workspace/organization for each connector and record it in SOURCE-MANIFEST.md.

If a connector is attached to the wrong account, mark it as blocked. Never perform any external actions without explicit user approval.

Required State and Resumption Files:
Create and maintain INGESTION-LOG.md and state.json so the process is fully resumable.

Required Compiler Process:
Use this repeatable process: parse → thread/group → classify → extract → canonicalize → rehydrate provenance → author → validate links → critic/audit

For large passes, use lighter models for early stages and the strongest model for synthesis and review.

Required Deterministic Machinery:
Create a _tools/ folder inside the vault with validation scripts for wikilinks, paths, secrets, source references, and required artifacts. Record results in VALIDATION-REPORT.md.

Redaction Policy:
Never copy secrets, API keys, tokens, or credentials into the vault. Prefer summaries and clear provenance.

Required Ingestion Plan:
- Ingest existing useful Markdown notes (prioritize people, projects, decisions, procedures, etc.).
- For email: Start with a small smoke test, then do broader passes only after user approval.

Hard Checkpoint 2:
After the initial smoke pass, show sample notes and ask for approval before continuing.

Required Vault Structure:
Include these folders: People/, Companies/, Projects/, Decisions/, Procedures/, Context Packs/, Sources/, _tools/, plus the required manifest and audit files.

Note Format:
Use clean Obsidian Markdown with YAML frontmatter, wikilinks, provenance, and clear structure. Do not invent facts.

Validation Hard Gates:
The vault is only complete when there are zero broken links, zero placeholder references, zero copied secrets, every note has provenance, and all validation scripts pass.

Execution Rules:
Work in phases, always resume by reading the log and state files first. Never make destructive changes or external writes without approval. Pause and ask the user before any broad or sensitive ingestion.

Quality Bar:
The final vault should be a structured, source-backed operating memory — not a raw data dump. It must help future agents clearly understand the user, their work, relationships, decisions, and procedures.

Completion Rule:
Do not mark the goal complete until the vault exists, all validations pass, and the required audit and manifest files confirm every requirement is satisfied.

💰 پتانسیل درآمدزایی این ورک‌فلو: ارزش واقعی این سیستم در مهندسی کانتکست (Context Engineering) است. شما می‌توانید همین فرآیند ساخت مغز دوم و سازماندهی اسناد را به عنوان یک سرویس گران‌قیمت به شرکت‌ها و کسب‌وکارهای کوچک ارائه دهید و برای پیاده‌سازی هر پروژه، مبالغی بالای ۵۰۰۰ دلار دریافت کنید.

🚀 مسیر دریافت هدایا بسیار ساده است: ۱. ایمیل خود را در کادر صفحه اول وب‌سایت ثبت کنید. ۲. بلافاصله لینک ورود مستقیم به کانال خصوصی تلگرام برای شما باز خواهد شد. ۳. هم‌زمان یک ایمیل حاوی لینک دانلود مستقیم هر ۴ کتابچه برای شما ارسال می‌شود. ⚠️ نکته مهم: حتماً پوشه Promotions و حتی Spam ایمیل خود را چک کنید تا فایل‌ها را از دست ندهید.

🟣 وضعیت قبل (انفعالی و فرساینده): ساعت‌ها سردرگمی در پورتال‌های دانشگاهی، نوشتن SOPهای کپی‌پیست شده و عمومی که اساتید در نگاه اول آن‌ها را رد می‌کنند، و از دست دادن فرصت‌های طلایی به علت خستگی ذهنی.

🔵 وضعیت مدرن (ماشینی و هدفمند): راه‌اندازی یک کارگزار خودمختار محلی که علایق تحقیقاتی و رزومه شما را در حافظه دائمی خود دارد، هر روز موقعیت‌های جدید را اسکن و فیلتر می‌کند، و برای هر پوزیشن یک پکیج رزومه و انگیزه نامه کاملاً یونیک و تخصصی خلق می‌کند.

{
  "mcpServers": {
    "higgsfield": {
      "command": "python",
      "args": [
        "-m",
        "higgsfield_mcp.server"
      ],
      "cwd": "/absolute/path/to/higgsfield_ai_mcp",
      "env": {
        "HF_API_KEY": "YOUR_HIGGSFIELD_API_KEY",
        "HF_SECRET": "YOUR_HIGGSFIELD_SECRET"
      }
    }
  }
}

[آپلود عکس خام در کلاود] ➔ [انتخاب مدل (Soul 2.0 یا Flux 2.0)] ➔ [اعمال پرامپت استایل] ➔ [درخواست تولید ویدیو (Kling 3.0)] ➔ [خروجی نهایی]

Apply a high-end luxury Scandinavian interior design style to this empty room. Maintain the exact architectural skeleton, window placements, ceiling heights, and structural walls of the input image. Replace the empty space with a clean boucle cream sectional sofa, minimalist light oak coffee table, and a neutral wool area rug. Add warm, diffused architectural lighting, a large fiddle-leaf fig plant in a ceramic pot near the window, and subtle luxury modern art on the main wall. Render in photorealistic 4K resolution, captured on a 24mm tilt-shift lens, shot in diffuse natural afternoon sunlight, Architectural Digest style, no artifacts, cinematic composition.

Renovate the materials in this kitchen space while maintaining the original layout and cabinet positions. Replace the old countertops with high-quality polished Calacatta marble slab. Change the flooring to light-toned polished herringbone hardwood. Modernize the cabinet faces to matte-finish forest green with brass minimalist handles. Enhance the lighting with modern under-cabinet LED strips and warm pendant lights over the island. Ensure high-fidelity rendering, 4K resolution, realistic shadows, photorealistic architectural photography.

Transform this daytime real estate exterior photo into a cinematic twilight (golden hour) shot. Keep the main structure of the villa exact. Turn on warm, inviting interior architectural lights showing through all windows. Add professional warm LED landscape lighting illuminating the facade and manicured front lawn. Replace the overcast flat sky with a rich, colorful sunset twilight sky with deep indigo and amber hues. The pool in the foreground should have realistic glowing water and sharp reflections of the sky and house. Shot on Hasselblad, 35mm tilt-shift lens, premium real estate listing style, 4K UHD.

Using the staged living room image as the first-frame anchor, generate a cinematic 5-second interior walkthrough video using Kling 3.0 model. The camera movement must be a slow, steady, ultra-stabilized forward push-in (dolly shot) traveling through the center of the living room towards the large glass windows showing the balcony view. Maintain absolute spatial, structural, and object consistency throughout the entire generation. No warping, stable lighting, smooth cinematic motion, broadcast quality, 60fps.

Write me a LinkedIn post about the AI tools I use daily. For context: I'm Navid, my audience is non-technical knowledge workers. My tone is direct, no fluff, contrarian hooks. Don't use corporate words like "leverage" or "unlock." Start with a statement, not a question. Structure it as a numbered list... Here are 3 examples of my past posts so you match my voice... [پیست کردن ۶۰۰ کلمه متن] ... okay now write it.

Read my 3 uploaded files first (

,

,

). Write a LinkedIn post about the AI tools I use daily, in my voice. Don't start yet - ask me clarifying questions (use AskUserQuestion) so we align on angle and audience.

"Use skill creator to build a skill for [توضیح تسک یا پروژه شما]" ۳. به سوالاتی که کلاود از شما می‌پرسد با دقت و جزئیات پاسخ دهید. ۴. کلاود یک فایل با فرمت

برای شما می‌نویسد؛ آن را بررسی و ذخیره کنید. ۵. فایل نهایی را از مسیر زیر در کلاود خود آپلود و برای همیشه فعال کنید:

۱۷۵ صفحه سناریوهای واقعی، کدهای آماده برای خط فرمان و نقشه راه تسلط بر بازیابی زمان در سال ۲۰۲۶.

🎨 چرا این نقشه راه هویت کاری شما را تغییر می‌دهد؟ شما دیگر یک اپراتور سردرگم نیستید که دکمه‌ها را شانسی امتحان کند؛ با این راهنمای بصری، به فرمانده ارشد ایجنت‌های خودران تبدیل می‌شوید که با سرعت نور و دقت $100\%$ سیستم‌ها را هدایت می‌کند.

🔮 چطور این تاریخچه را به یک آینه تبدیل کنیم؟ مدل‌های معمولی با رفتارهای ما برخورد سطحی می‌کنند (سیستم ۱)، اما کلاود با فرمول سیستم ۲ دنیل کانمن می‌تواند نقش یک منتقد و معمار ارشد را بازی کند. این پرامپت انگلیسی ۶ فازی، تاریخچه تمام چت‌ها و پروژه‌هایتان را جراحی می‌کند، فرضیاتی درباره شخصیت کاری شما می‌سازد، مچتان را با سند و مدرک (Receipts) می‌گیرد و در نهایت ابزارهای کاری‌تان را بر اساس هویت واقعی‌تان بازسازی می‌کند.

<overview>
People lie in journals. They perform in therapy. Nobody performs for a coding agent.

On this machine sits the most honest record of my mind that has ever existed: every session I've run with AI agents. What I build, what I abandon, what I ask for three times and never automate, what I circle and never touch. You are intelligent enough to read that record and see the shape of the person who left it.

Your job is to change my life with it. Not with advice. With accuracy. Advice I can ignore; a true pattern with my own timestamps on it, I cannot.

Work through six phases, in order:
Phase 1: Excavate — locate every session archive on this machine.
Phase 2: Distill — mine the archives in guarded passes into an evidence file.
Phase 3: Interview — test what you see against me directly.
Phase 4: The Mirror — tell me who I am. Evidence, then verdict.
Phase 5: Leverage — where my hours die, and where they multiply.
Phase 6: Residue — leave artifacts, and with my consent, rebuild my tools around who I turned out to be.

Never skip a phase. Never advance past a gate without meeting it.
</overview>

<phase_1 name="Excavate">
<process>
Search for AI agent session archives. Check, at minimum:
~/.claude/projects/ (Claude Code JSONL), ~/.claude/history.jsonl,
~/.codex/sessions/, ~/.config/opencode/, ~/.local/share/opencode/,
~/.pi/ or ~/.pi.dev/, ~/.omp/, ~/.grok/, ~/.hermes/, ~/.openclaw/,
plus any *.jsonl or session directories under ~/.config/ and ~/.local/share/ that look like agent transcripts.
For each source found, record: tool name, path, file count, total size, date range (oldest → newest file mtime).
</process>
<output>A one-screen inventory table of every source found.</output>
<gate>Show me the inventory and your mining plan (which sources, what sampling). Wait for my go.</gate>
</phase_1>

<phase_2 name="Distill">
<budget>
These archives are far larger than your context. Never read a session file end to end. Never load raw logs into the conversation.
- Read at most 150 lines per file, at most 200 files total.
- Sample deliberately: the 15 most recent sessions, the 10 oldest, and 20 spread across the middle.
- Use grep/rg for pattern sweeps across everything instead of reading: correction phrases ("no, I meant", "that's not what", "again", "stop"), frustration, repeated identical requests across weeks, projects that appear 3+ times then vanish, times of day, "just do it" vs long deliberation.
- After every 25 files, append findings to evidence.md and drop the raw text from your working memory.
</budget>
<process>
Build evidence.md as you go, with verbatim quotes (short), dates, and counts, organized as:
1. Recurring themes — what I return to again and again
2. Abandonment graveyard — what I start and never finish
3. Correction patterns — what I fix in the AI's work, and what that says I care about
4. Repetition tax — what I ask for over and over that should have been automated the second time
5. Rhythm — when I do my best work, when I spiral
6. Blind spots — what is conspicuously absent from these logs. Absence is data.
Every claim in evidence.md carries at least one dated receipt. A pattern needs 3+ occurrences to count. What happened once is noise; what happened eleven times is character.
</process>
<gate>evidence.md exists, every section populated or explicitly marked "insufficient data". Do not interpret yet. Evidence collected under a conclusion is contaminated.</gate>
</phase_2>

<phase_3 name="Interview">
<process>
Form your 5 strongest hypotheses about me from the evidence. Do not state them. A conclusion I reach myself will move me; the same conclusion handed to me, I will argue with. So test each hypothesis with one question built to make me do the realizing.
One question at a time. Wait for each answer. When my answer contradicts the evidence, show me the receipt and ask again — the gap between what I say and what I did is the most interesting thing you will find.
</process>
<gate>All 5 hypotheses tested against my own words. Record confirmations and contradictions in evidence.md.</gate>
</phase_3>

<phase_4 name="The Mirror">
<process>
Now tell me who I am. Cover: what I actually believe (belief is what I did with my hours, not what I said), how my thinking moves (where it's fast, where it loops), what I'm genuinely good at, what I avoid and what the avoidance is protecting, and one thing I likely do not know about myself — the thing the record shows on every page and I have never once said out loud.
Every observation cites its receipts. Deliver the hardest truth last, and deliver it once. A truth repeated becomes a lecture; a truth stated once and left in the room does its own work.
</process>
<gate>I respond. If I push back, argue from evidence — do not fold to keep me comfortable. Comfort is not what this is for.</gate>
</phase_4>

<phase_5 name="Leverage">
<process>
From the same evidence, produce the work analysis:
- WASTE: where my hours die — with the receipts (repetition tax, manual work an agent should own)
- DELEGATE: what to hand to AI permanently, ranked by hours recovered per week
- FOCUS: the one or two things only I can do, where the record says my output is exceptional. Everything else is a candidate for the other lists.
- DROP: what to stop entirely — projects and processes whose receipts show cost and no return
- KEEP: processes that genuinely work — protect them
- RHYTHM: when to schedule deep work vs admin, from the timestamps. My calendar should obey the data, not the other way around.
</process>
<gate>Each item carries receipts and a concrete first action. Insight without a next action is entertainment.</gate>
</phase_5>

<phase_6 name="Residue">
<process>
1. Write mirror.md — the Phase 4 analysis, written to be reread in six months by someone who has forgotten this conversation.
2. Write roadmap.md — the Phase 5 analysis as a 30-day plan: what to drop this week, what to delegate this month, what to protect daily.
3. Propose changes to my agent configs (CLAUDE.md, AGENTS.md) and draft up to 3 custom skills/commands that kill the repetition tax you found. Show every change as a diff first. Write nothing to existing config files until I approve each diff. New files require one approval for the batch.
This is where the mirror becomes a lever: tomorrow morning my tools work differently because of who the record showed I am.
</process>
<gate>All three artifacts delivered; config changes applied only where approved.</gate>
</phase_6>

<voice>
Speak plainly and with weight. Short sentences. No filler, no flattery, no hedging.
Prefer questions that make me see it over statements that tell me. When you do state, state once and let it land.
Aphorism is earned: compress an insight only after its evidence is on the table. An aphorism without receipts is a fortune cookie.
Never diagnose or pathologize. You describe patterns in logs; I decide what they mean.
Contrast: "You seem like a curious person who loves learning!" — worthless. "In 41 sessions you built research systems. In 0 sessions you shipped one to a user. What are you researching permission for?" — that is the standard.
</voice>

<global_constraints>
- Everything stays on this machine. Never send session data to any external service, tool, or URL.
- Never quote anything sensitive (keys, credentials, names of third parties) into chat or artifacts.
- Insight over coverage: 5 true patterns beat 20 plausible ones. If the evidence is thin, say "insufficient data" — never pad. A false insight delivered with weight is the one failure this cannot recover from.
- If my history is small (<20 sessions), say so, run the same phases on what exists, and lower your confidence accordingly.
</global_constraints>
Begin with Phase 1. Do not read any file contents until I approve the mining plan.