OkayTeacher
EN English 한국어 日本語 中文 हिन्दी বাংলা اردو Español Português Français Deutsch Русский العربية Bahasa Indonesia Tiếng Việt ไทย Türkçe

How to enable notifications

Notifications are unavailable in this browser or on this address. Try a supported browser on the secure SONUB site.

If notifications are blocked, allow them in your browser settings.

  1. Open the site controls beside the address bar, or your browser’s site settings. Set Notifications for this site to Allow.
  2. In your device settings, allow notifications for your browser and check Do Not Disturb or Focus.
  3. Return to SONUB, reload the page, and use the bell to enable notifications.

On iPhone or iPad, add SONUB to your Home Screen, open it there, then allow notifications.
Tools

Tool Master

, , , , and agy all run the same agent loop and share the same habits — AGENTS.md, slash commands, plan mode, approvals and . Learn the common parts once and you can use any of them.

Harness — three views
A student holds one glowing skill cartridge whose cables plug into six different terminal robots, and all six light up the same way
Claude Code + Codex

Recommended use — what both official guides say

Anthropic and OpenAI each publish best practices for their coding tool. Put side by side, they say almost the same thing: pick a strong model at High effort, give the a way to check its work, keep lasting rules in a file and keep the clean. This tab joins the two guides into one (checked 2026-10-26).

A student at a desk with a friendly AI orb; a path leads past a plan clipboard, a dial turned up, a screen of green check marks and on to a finish flag, while potholes beside the path are covered by planks
  1. Recommended modelsOpus 5.5 and GPT-6.1 Sol, both at High
  2. Six good habitsAsk → plan → check → rules → context → scale up
  3. Ten common mistakesEach one with the habit that fixes it
Model and effort

Recommended models — as of November 2026

Both let you choose the and how hard it thinks (effort). A stronger model at a higher level does better on hard work but is slower and uses more of your plan. For development, start with these two settings.

Claude Code

Opus 5.5Effort High

Effort levels, low to high — the highlighted one is recommended
  1. low
  2. medium
  3. high — recommended
  4. xhigh
  5. max

opus is the latest Opus (Opus 5.5 on the ). Its default effort is medium, so raise it to high yourself. sonnet suits everyday and haiku simple jobs; fable (Fable 5.1) is for the hardest, longest work and must be chosen by hand.

~/.claude/settings.json
{
  "model": "opus",
  "effortLevel": "high"
}
Start with
claude --model opus --effort high
Switch while chatting
/model · /effort
Source (new window)

Codex CLI

GPT-6.1 SolEffort High

Effort levels, low to high — the highlighted one is recommended
  1. low
  2. medium
  3. high — recommended
  4. xhigh
  5. max
  6. ultra

gpt-6.1-sol gives near-Astra results at a lower cost, when your account has it. gpt-6-astra is for the hardest end-to-end work and gpt-6-luna for focused, repeated jobs. The 's low is called Light in the app, and ultra works with .

~/.codex/config.toml
model = "gpt-6.1-sol"
model_reasoning_effort = "high"
Start with
codex -m gpt-6.1-sol
Switch while chatting
/model
Source (new window)

When to go lower or higher

Small, repeated jobs (renaming, a typo, a log line) run faster and cheaper on a lower effort or a lighter model. Raise it to xhigh or max — or pick fable or gpt-6-astra — only for long, difficult, multi-step work, and come back to High afterwards.

Best practices

Six good habits — in the order you work

These six habits appear in both official guides. Each card shows how to do it in and in .

  1. Step 1 · Ask with four parts

    Say the goal, the context (files, docs, the full error — attach files with @), the limits and when it is done. Point to an existing pattern to copy. Keep investigations narrow so the agent does not read hundreds of files.

    Claude Code
    @file · cat error.log | claude -p "…"
    Codex CLI
    @file

  2. Step 2 · Plan hard work first

    For work that touches many files or that you do not know well, switch to plan mode, read and plan, adjust the plan, then build. For a big feature, let the agent interview you and write a spec. If you can describe the change in one sentence, skip the plan.

    Claude Code
    Shift+Tab · claude --permission-mode plan
    Codex CLI
    /plan · Shift+Tab

  3. Step 3 · Let it check its own work

    Give it something that passes or fails — tests, a build, a to compare — and ask it to show the evidence. Before you call the job done, have a fresh reviewer read the .

    Claude Code
    /code-review
    Codex CLI
    /review

  4. Step 4 · Keep lasting rules in files

    Rules you repeat go into AGENTS.md or CLAUDE.md — short, with the build and test commands. Knowledge needed only sometimes becomes a , outside information comes through , and must-happen steps become hooks.

    Claude Code
    CLAUDE.md · .claude/skills · claude mcp add
    Codex CLI
    AGENTS.md · .agents/skills · codex mcp add

  5. Step 5 · Keep the context clean

    Use one conversation per piece of work, clear it between unrelated tasks and compact long ones. If two corrections fail, start fresh with a better request — a clean session beats a long one full of failed attempts.

    Claude Code
    /clear · /compact · /btw · /rewind
    Codex CLI
    /new · /compact · /fork

  6. Step 6 · Scale up and work in parallel

    Run it from scripts and without the chat screen, give each parallel job its own , and do your own work while it runs instead of watching every step. Schedule a recurring job only after it works reliably by hand.

    Claude Code
    claude -p · git worktree
    Codex CLI
    codex exec · git worktree
A request with four parts — works in both tools
Goal: Remove an item from the cart when its quantity becomes 0.
Context: @src/cart.ts @tests/cart.test.ts — the total is NaN today.
Constraints: Keep the public API. No new packages.
Done when: a new test covers quantity 0 and the tests pass.
Show me the test output as evidence.

Goal · context · limits · done when, plus the evidence you want to see. Replace the files and the goal with your own.

Common mistakes

Ten common mistakes — and the habit that fixes each

The Claude Code guide lists five failure patterns and the Codex guide eight. Joined by meaning, they make ten. The chips show which official list each comes from.

  1. Mixing unrelated tasks in one conversation, or running a whole project in one chat — the context fills with noise.

    Claude CodeCodex CLI

    Fix: One conversation per clear outcome; clear or open a new one between unrelated tasks.

    Habit 5 — Keep the context clean

  2. Correcting the same thing again and again — the context fills with failed attempts.

    Claude Code

    Fix: After two failed corrections, start fresh with a better first request that includes what you learned.

    Habit 5 — Keep the context clean

  3. Stuffing lasting rules into every request, or letting the rules file grow so long that important rules get lost.

    Claude CodeCodex CLI

    Fix: Move lasting rules into AGENTS.md or CLAUDE.md and keep it short; delete what the agent already does right, or turn it into a hook.

    Habit 4 — Keep lasting rules in files

  4. Trusting work you cannot check — no build or test commands given, so the code looks right but misses .

    Claude CodeCodex CLI

    Fix: Always give a way to check (tests, scripts, screenshots) and write the build and test commands down. If you cannot check it, do not ship it.

    Habit 3 — Let it check its own work

  5. Asking it to "investigate" with no limit — it reads hundreds of files and fills the context.

    Claude Code

    Fix: Narrow the scope in the request, or hand the investigation to a subagent.

    Habit 1 — Ask with four parts

  6. Skipping the plan on complex, multi-step work.

    Codex CLI

    Fix: Start in plan mode and agree on the plan before any code changes.

    Habit 2 — Plan hard work first

  7. Giving the agent full access to your computer before you understand the .

    Codex CLI

    Fix: Start with the default and loosen them only when you need to.

    Habit 4 — Keep lasting rules in files

  8. Running several live jobs on the same files at once.

    Codex CLI

    Fix: Give each parallel job its own Git worktree.

    Habit 6 — Scale up and work in parallel

  9. Scheduling a recurring job before it works reliably by hand.

    Codex CLI

    Fix: Run it by hand until it is reliable, then schedule it.

    Habit 6 — Scale up and work in parallel

  10. Watching the agent step by step instead of working in parallel.

    Codex CLI

    Fix: Hand the job over with a clear and do your own work meanwhile.

    Habit 6 — Scale up and work in parallel

Sources

Checked in the official documents on 2026-10-26. The recommended models are SONUB's choice as of November 2026; models change often, so check the model pages too.

Keep going