vibecodeit

Build Inbox Zero

KINDAreplaces $20/mosaves $240/yrback to the verdict

0%0 of 21 items done

Saved on this device only. Tick prerequisites first, then work the phases in order · do not start one until the checks above it pass.

Build a read-only email triage desk with reviewed draft replies.

estimated effort multi-daythe files for this build are in the project pack

RuntimePython 3.12+ and FlaskStorageSQLite through Python sqlite3InterfaceJinja HTML templates, CSS and vanilla JavaScriptVerificationPython unittest and browser acceptance fixturesGenerationOllama local HTTP API

Before step 1

Everything below is assumed from the first step. Tick each one when you actually have it, not when you plan to.

  1. installPython is free; this local prototype requires no hosting subscription.

    Why The local backend, tests and storage use Python.

    Get it Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. open ↗

    Verify python --version reports 3.12+ and python -c "import sqlite3" succeeds.

  2. installNo paid service required for this local step.

    Why You need to view the local interface and edit generated project files.

    Get it Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository.

    Verify You can create a text file in the project folder and open browser developer tools.

  3. have readyNo paid service required for this local step.

    Why This fixture makes the first end-to-end check reproducible.

    Get it Create synthetic sample data before implementation: Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records.

    Verify The fixture files and expected outcomes exist and can be inspected without a vendor account.

  4. decideNo paid service required for this local step.

    Why The full commercial product is larger than this guide.

    Get it The deliverable is a read-only email triage desk with reviewed draft replies. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first.

    Verify You can name the primary workflow and the vendor features this version deliberately leaves out.

  5. installNo cloud inference fee for this local configuration; you supply disk space, compute and electricity.

    Why Generation requires a running model; ordinary editing remains usable while it is unavailable.

    Get it Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. open ↗

    Verify ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download.

Data model

Create these before the first phase that stores anything. Changing a table later is the expensive kind of change.

- messages(id,message_id,subject,sender,body,received_at)
- classifications(message_id,category,reason,model,revision)
- rules(id,sender_pattern,category,enabled)
- drafts(id,message_id,text,state)
- actions(id,message_id,proposed_action,state)
- Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them.
- Acceptance fixture: Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions.

Environment variables

These go in a .env file the app reads at startup. The pack's .env.example is this table as a file · copy it, never commit the filled-in version.

VariableNeededExampleWhere the value comes from
DATA_DIRrequired./data/inbox-zeroA new private folder this application creates on first run; never serve it as static files.
SECRET_KEYsecretrequiredreplace-with-a-random-secretGenerate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env.
APP_MODErequiredindieUse indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured.
SITE_URLrequiredhttp://127.0.0.1:5000The origin used for local forms and links; replace with the chosen HTTPS origin in product mode.
OLLAMA_URLrequiredhttp://127.0.0.1:11434Keep the inference service bound to loopback; the backend calls it, never the public browser.
LOCAL_MODELrequiredreplace-with-installed-local-modelCopy the exact non-cloud name from ollama list; preflight must reject this placeholder.

The build, in order

  1. Local foundation and data contract

    Create the runnable local foundation for a read-only email triage desk with reviewed draft replies, including the real schema and acceptance fixture.

    1. Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch.

      Files app.pyrequirements.txt.env.example.gitignore

      terminal
      python -m venv .venv
python -m pip install Flask Flask-WTF python-dotenv waitress tzdata
python -m pip freeze > requirements.txt
python -m flask --app app run --host 127.0.0.1

    2. For database-backed state create schema.sql and db.py using this model: messages(id,message_id,subject,sender,body,received_at); classifications(message_id,category,reason,model,revision); rules(id,sender_pattern,category,enabled); drafts(id,message_id,text,state); actions(id,message_id,proposed_action,state). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions. Re-running init must not erase data.

      Files schema.sqldb.pymanage.pyfixtures/README.md

      terminal
      python manage.py init
python manage.py seed

    3. Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now.

      Files app.pytemplates/base.htmltest/test_foundation.py

    4. Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable.

      Files providers/local_model.pyscripts/model_probe.py

      terminal
      python scripts/model_probe.py
    done when · tick each as it passes
    watch out
    • The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation.
    next phase

  2. Private import

    Private import for Inbox Zero: Parse manually exported .eml files and deduplicate Message-ID while preserving raw originals outside the public directory.

    1. Parse manually exported .eml files and deduplicate Message-ID while preserving raw originals outside the public directory.

      Files features/private_import.pytemplates/private_import.html

    2. Render text bodies with remote images disabled and strip active HTML; do not connect mailbox mutation permissions.

      Files features/private_import.py

    3. Use Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions. Check: Importing the same mailbox sample twice preserves three messages. Then check: Viewing the hostile message makes no remote image request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser.

      Files test/test_private_import.py

      terminal
      python -m unittest discover -s test
    done when · tick each as it passes
    watch out
    • Manual import is the deliberate v1 boundary; no background mailbox cleanup is performed.
    next phase

  3. Explainable triage

    Explainable triage for Inbox Zero: Apply explicit sender rules first and optionally ask the local model for one of receipt/action/newsletter/unknown with a reason.

    1. Apply explicit sender rules first and optionally ask the local model for one of receipt/action/newsletter/unknown with a reason.

      Files features/explainable_triage.pytemplates/explainable_triage.html

    2. Treat message contents as untrusted input, validate category JSON and expose a review queue for uncertain decisions.

      Files features/explainable_triage.py

    3. Use Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions. Check: Instructions inside the hostile email cannot change app rules or access files. Then check: A malformed model reply becomes unknown rather than silently archived. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser.

      Files test/test_explainable_triage.py

      terminal
      python -m unittest discover -s test
    done when · tick each as it passes
    watch out
    • Classification is a suggestion, not authorization to delete or unsubscribe.
    next phase

  4. Draft and export

    Draft and export for Inbox Zero: Generate a reply draft from a selected message and user intent; show it for manual editing without sending.

    1. Generate a reply draft from a selected message and user intent; show it for manual editing without sending.

      Files features/draft_and_export.pytemplates/draft_and_export.html

    2. Export approved draft text and a proposed-action CSV the user can review in their actual mail client.

      Files features/draft_and_export.py

    3. Use Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions. Check: No interaction in the app sends, deletes or archives a real email. Then check: Rejecting a proposed action leaves the imported source unchanged. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser.

      Files test/test_draft_and_export.py

      terminal
      python -m unittest discover -s test
    done when · tick each as it passes
    watch out
    • Automatic Gmail cleanup, outbound delivery and continuously maintained OAuth integrations are excluded.
    next phase

  5. Portable delivery and clean-start proof

    Finish the Inbox Zero replacement with a documented first-run path and a recoverable export.

    1. Document prerequisites, every configuration variable, data locations and the three domain workflows: Private import; Explainable triage; Draft and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them.

      Files README.md.env.example

    2. Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for inbox-zero. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: Three exported .eml messages: a receipt, a personal request and a message containing malicious model instructions. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy.

      Files OPERATIONS.mdscripts/backup.py

    3. Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete.

      Files README.mdverification.md

      terminal
      python -m pip install -r requirements.txt
python -m unittest discover -s test
    done when · tick each as it passes
    watch out
    • Export without an import or restore rehearsal is not verified portability.
what this build does not replace
after v1, if you want it

Need the files? The project pack on the verdict page hands your agent the whole brief · more email.