Beginner Steps. Advanced AI.
Published guideUpdated
Chapter 12 of 20Plan
Plan small build stages
Ask Codex for a build plan with small tasks and checks you can see. Approve the first stage when ready.
Build a little, check it, then move to the next stage.
Follow the pictures
Illustrated examples. Your app may look different. Tap an image to enlarge it.
-
Check the planning files
Send the build-plan prompt. Ask Codex to read your instructions, skills, and planning files, and flag missing information.
Illustrated example - Codex
- Copy prompt → Read instructions and plans → Resolve questions
Look for: Codex identifies missing or conflicting decisions before building.
More help with this action
Use the implementation-plan prompt to read AGENTS.md, planning documents, and skills. Ask Codex to flag conflicting decisions and essential missing information first.
Step by step
- Open the linked prompt and paste it into your fieldnotes-studio chat.
- Ask Codex to read AGENTS.md and the five planning files: website-brief.md, sitemap.md, content.md, architecture.md, and design-direction.md.
- Use clean-code, website-testing, and website-security. Resolve essential gaps and conflicting choices before scaffolding.
You should now see: Codex identifies missing or conflicting decisions before building.
-
List the stages
Ask Codex to save docs/build-plan.md using the staged planning prompt. Build Home before the remaining pages.
Illustrated example - Plan
- Setup → Home → Other pages → Checks → Later publication
Look for: Small build stages, with publication kept separate.
More help with this action
Create docs/build-plan.md using the staged planning prompt: setup, shared layout and Home, remaining pages, testing, security, polish, automated checks, and separate publication.
Step by step
- Create stages for setup, shared layout and Home, remaining pages, testing, security, polish, and automated checks.
- Complete Home before repeating the pattern on the other pages.
- Keep publication as a separate later stage requiring your review and decision.
You should now see: Small build stages, with publication kept separate.
-
Give every stage a clear finish
Ask for goals, files, dependencies, checks, and a saved Git milestone. Record commands that actually exist.
Illustrated example - Write
- Stage → Output → Check → Git milestone
Look for: Each stage says what changes and how to verify it.
More help with this action
For each stage, record goals, files, dependencies, browser checks, and a Git milestone. Specify real build and check commands to establish or run; require honest reporting of failed or unavailable checks.
Step by step
- For each stage, ask what it produces, which files it changes, and what it depends on.
- Name the browser checks and actual build/check commands to establish or run.
- Require honest reports of failed or unavailable checks and a reviewed Git milestone.
You should now see: Each stage says what changes and how to verify it.
-
Use checks you can observe
Adapt the acceptance checklist for links, phone layout, keyboard focus, images, and contact. Use W3C early checks.
Illustrated example - Check
- Routes → Navigation → Phone → Keyboard → Contact
Look for: Checks describe things you can actually inspect.
More help with this action
Adapt the example acceptance checklist for routes, navigation, keyboard focus, phone readability, image alternatives, and real contact details. Use W3C early accessibility checks for observable evidence.
Step by step
- Copy the example acceptance checklist and adapt it to your website.
- Use observable checks: four routes load, links reach the intended pages, keyboard focus is visible, and mobile content does not overflow.
- Include appropriate image alternatives, real contact details, and documented remaining issues.
You should now see: Checks describe things you can actually inspect.
-
Plan real automated checks
Ask Codex to plan a successful build and useful tests, including any missing package.json check scripts.
Illustrated example - Plan
- Name checks → Create missing scripts during the build → Run and report results
Look for: The plan names the checks, when to create missing scripts, and how to report results.
More help with this action
Plan a successful production build and relevant automated checks. Include any missing package.json scripts as a build task; do not assume npm test already exists.
Step by step
- Ask Codex to inspect package.json rather than assume npm test already exists.
- Plan the tools and scripts required for useful code and browser checks.
- Require a successful production build and browser inspection of the built version.
You should now see: The plan names the checks, when to create missing scripts, and how to report results.
-
Approve the first stage
Review the acceptance checklist. Approve only the first build stage, then ask Codex to commit the plan.
Illustrated example - Decide
- Review plan → Approve first stage → Save → Build locally
Look for: You know the first task; publication still waits for later review.
More help with this action
Review the plan against the acceptance checklist and approve the first build stage only. Keep publication pending your later preview review, then commit the planning milestone.
Step by step
- Read docs/build-plan.md and compare it with your brief and acceptance checklist.
- Approve the first build stage when you understand its output and checks.
- Ask Codex to commit the reviewed plan. Keep publication pending your later preview review.
You should now see: You know the first task; publication still waits for later review.
Why this step matters
A useful plan is more specific than 'create pages, test, deploy'. It names the files or behavior to create, dependencies between tasks, and the evidence needed before moving on. Building one complete page first exposes design and setup problems before they spread across the website.
Acceptance criteria describe what you must be able to observe. For example, 'all four navigation links reach their intended page' is verifiable. 'The website is fully secure' is an unsupported absolute claim. Security and accessibility need relevant checks, documented findings, and clear limits.
Basics, explained
Acceptance criteria
Specific conditions you can check to decide whether a feature or version is finished.
Dependency
Something a task needs before it can work, such as a shared layout before pages use that layout.
Milestone
A small, completed stage saved in Git so you have a known point to review or recover.
Production build
The output intended for hosting, created from the source. It needs verification in addition to the development preview.
Ask your agent
PromptCreate an executable plan
Read AGENTS.md and the five planning files in docs/: website-brief.md, sitemap.md, content.md, architecture.md, and design-direction.md. Use the clean-code, website-testing, and website-security skills. Save docs/build-plan.md with small stages, dependencies, intended files, meaningful acceptance criteria, required check scripts, browser checks, and Git milestones. Build Home completely before repeating patterns. Show conflicting assumptions and missing inputs. Keep deployment as a later approval step. Create the plan only; do not scaffold until I approve the first stage. Files & commands
textExample acceptance criteria
[ ] Home, About, Services, and Contact load at their planned URLs
[ ] Header and footer navigation reach the intended pages
[ ] Keyboard users can reach links and see focus
[ ] At 360px and 1280px, content has no horizontal overflow
[ ] Contact shows my real inbox and the matching email link
[ ] Images have appropriate alternatives and known sources
[ ] Established checks and the production build pass
[ ] Browser checks and remaining issues are documented
[ ] Publication awaits my approval after review If something goes wrong
- The plan promises quality without saying how to check it.
- Ask for evidence tied to each claim: routes tested, viewport widths inspected, commands run, security findings reviewed, and known limits recorded.
- Codex begins building while you are still reviewing the plan.
- Stop that task, inspect any changes, and restate the current boundary: finish the plan and wait for approval of the first build stage. Preserve useful changes before deciding how to proceed.
Official links & further reading
Personal notes
Add questions, decisions or ideas for your website. Saved in this browser when available; export your notes to keep a copy. Never enter secrets.
Downloads & saved progressGuide, notes and personal checks
Download the complete guide or export your notes from every chapter. Instructions last reviewed: .
Checks and notes stay in this browser, separately for each language. Export your notes to preserve them. Never enter API keys or other secrets here.
NotesNotes as Markdown
Clipboard access is unavailable. Copy the visible, selected text below using your keyboard or browser menu.
0 of 65 checks marked across the guide
These are your saved personal checkmarks. They do not run tests or verify security, and are separate from the chapter position bar above.
Starter filesWorking instructions and four skills
These templates give your agent a starting set of working instructions. Review them, adapt them to your website, and save each file at the exact path shown, relative to your project folder.
A downloaded skill is an instruction file. It does not install a test runner, run a security scan, or prove your site is safe. The guide shows how to set up and check that work.
Download the instruction files in the language of this guide. Keep the technical filenames and paths as shown.
Download all starter filesFileAGENTS.md
# Website working agreements
This project follows the website brief and acceptance criteria we have agreed with its owner. Use the existing technology choices unless a concrete requirement calls for a change.
## How to work
- For a substantial feature, explain the proposed changes and verification plan before implementing it. Complete authorized local work in small, reviewable stages.
- Read the files relevant to the task. Keep unrelated pages and configuration intact.
- Explain new technical terms in plain language when reporting to the owner.
- Use the repository's website-design, clean-code, website-testing and website-security skills when their workflows apply.
- Record important decisions and unresolved content in the project's notes. Do not invent business facts, endorsements or publishing rights.
## Verification
- Inspect package.json to find the actual build, type-check and test commands. Do not invent a successful check or create a meaningless test just to make a command pass.
- Run checks appropriate to the change. Local tests use disposable fixtures and have no production access; run them and repair failures caused by the requested change without asking at every step.
- Verify visitor interactions in a browser when browser tools are available. Report checks that remain unavailable or incomplete.
- Show the owner a working local preview and summarise changed behaviour, evidence and remaining limitations.
## Credentials and publication
- Keep API keys and other secrets out of browser code, prompts, logs and Git. Store local secrets in ignored files or the chosen secret store.
- Local build and test work is authorized. Publishing the site, sending a real message, processing a payment or changing production data requires the owner's authorization for that action.
- Preserve a recoverable working version before release. Describe how to restore it.
These are starter agreements for a new tutorial project. Adapt them to the owner's actual requirements and existing authorization.
File.agents/skills/website-design/SKILL.md
---
name: website-design
description: Develop or refine a website's visual direction and responsive interface from its brief, content and existing design. Use for page design or visual implementation.
---
Read the website brief and any existing design notes relevant to the requested page. Work within the user's brand, content and technology choices.
When establishing a new direction, propose typography, a small colour palette, a spacing rhythm and a sample page. Explain how these choices support the audience and main visitor action. Use real content to judge hierarchy and line lengths.
Implement reusable elements for navigation, headings, buttons and repeated content. Give primary actions a clear visual hierarchy. Preserve visible keyboard focus, readable contrast and usable labels. Design narrow screens alongside desktop screens; check long headings, navigation and tap targets in a browser.
Use semantic HTML before adding custom interaction. Keep motion optional and respect reduced-motion preferences. Use assets with known permission to publish; record their sources. Do not invent client testimonials, achievements or business facts.
Before expanding a design across all pages, show the first complete page at desktop and mobile widths. Describe the main design decisions and any unresolved content. When a browser tool is unavailable, report that visual verification is still pending.
File.agents/skills/clean-code/SKILL.md
---
name: clean-code
description: Implement or refactor website code into understandable components using the project's existing stack and conventions. Use for website implementation or maintainability work.
---
Read the relevant files and package scripts before choosing an implementation. Preserve working behaviour outside the requested change. Prefer the existing stack and dependencies when they meet the need.
Keep page content separate from repeated layout where that makes editing easier. Name components, variables and functions for their purpose. Use shared components for repeated navigation and page elements; avoid abstraction for a single trivial use.
Handle empty, invalid, loading and error states for interactions that need them. Use native browser controls and semantic HTML when they serve the interaction. Avoid fake form submission, simulated success messages and dead links.
Use type checking and the project's formatting or lint rules where configured. When adding a package, explain its purpose and any new maintenance or runtime requirements. Keep generated build output, dependencies and local environment files out of version control.
Run the existing checks relevant to the change, including a production build when output can change. Summarise changed behaviour, verification results and remaining limits. Explain the main files in plain language so a beginner can find and edit their content.
File.agents/skills/website-testing/SKILL.md
---
name: website-testing
description: Verify website changes through visitor journeys, appropriate automated tests and browser checks. Use when testing a website, investigating a failure or preparing a release.
---
Start from the brief and observable acceptance criteria. Inspect existing test and build commands; do not assume that a script exists. Choose checks based on the changed behaviour and the cost of failure.
Exercise the main visitor journey and affected links, navigation and forms. Include invalid input and relevant error states. For a contact form, verify actual delivery in the agreed test destination before reporting that it works. For an email link, explain that it opens the visitor's configured email app and does not send a message automatically.
Check narrow and wide screens in a browser. Include keyboard navigation, visible focus, accessible names, zoom and horizontal overflow. Automated accessibility results complement these manual checks and do not establish complete accessibility conformance.
Add automated tests for important behaviour or demonstrated regressions. Test observable outcomes and meaningful failure cases; avoid tests that merely repeat the implementation or match incidental wording. Use disposable test data and local fixtures. Never send real messages, charge payments or alter production data without the user's authorization.
Reproduce a failure, fix its cause and rerun affected checks. Report commands run, results, browser checks performed and anything not checked. A successful build shows that the site can be generated; verify visitor behaviour separately. Never report a check as passed when it was skipped or unavailable.
File.agents/skills/website-security/SKILL.md
---
name: website-security
description: Review a website's secrets, dependencies, inputs, permissions and deployment configuration, and repair scoped security findings. Use for requested security review or release preparation.
---
Identify the site's relevant surfaces: static pages, forms, backend routes, authentication, third-party scripts and stored data. Scope review to the actual architecture and authorized environment.
Keep credentials out of browser code, logs, prompts and Git. Distinguish build-time public configuration from server secrets. If a key was committed or exposed, stop using it, explain that deleting the file does not revoke the key, and have the owner revoke or rotate it before further use. Do not print the credential in your report.
Inspect applicable dependency advisories and assess whether the affected package and vulnerable behaviour are used. Repair within the project's compatible versions and rerun affected checks. Avoid automatic forced upgrades that may break the website.
For backend interactions, validate inputs on the server, encode output appropriately, and check authentication and authorization separately. Consider abuse controls for public forms or AI endpoints. An OpenAI API key belongs on the server; publishing a static site does not provide a secret server environment.
Check HTTPS and applicable security headers at the actual hosting layer. Collect only the data the feature needs, and explain its destination and retention. Do not claim legal compliance from a code scan.
Report each finding with its location, plausible impact, fix and verification. State review scope, tools used, unresolved findings and inaccessible surfaces. A clean scan is evidence about that scan's scope, not a guarantee that the website has no vulnerabilities. Do not scan third-party systems or deploy changes outside the authorized task.