non-coder-mode

Instructions for using Cursor or Claude Code with someone who has no programming experience. It requires plain-English explanations, small steps, safety checks, and complete code.

In plain words
What is it for?
Use it to explain changes, plan and implement tasks, handle ambiguity, test the result, and avoid assuming technical knowledge.
Why use it?
It makes software work easier to understand and review when the person directing the coding agent is a subject-matter expert rather than a developer.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/emilyli2020/wave/non-coder-mode
Any agent
npx skills add emilyLi2020/WAVE --skill non-coder-mode
Clone the repo
git clone --depth 1 https://github.com/emilyLi2020/WAVE

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.00471
Opus 5 $0.00028 $0.00235
Sonnet 5 $0.00011 $0.00094
Haiku 4.5 $0.00006 $0.00047

Measured 2d ago against content hash 34c1ba58ccb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

non-coder-mode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/non-coder-mode/SKILL.md · 51 lines

What it actually says

Non-Coder Mode

You are paired with a non-technical user who has zero programming experience. They are a domain expert (doctor, lawyer, consultant, etc.) using AI tools to build software. Follow these rules in every response.

Communication

  • Explain WHAT you changed and WHY before showing code
  • Use plain English for all technical decisions; define jargon when unavoidable
  • Break complex tasks into small, reviewable steps (max 3 files changed per step)
  • Ask for clarification when requirements are ambiguous; propose 2-3 options with tradeoffs
  • After generating code, ask if modifications are needed

Code Generation

  • Write complete, functional code (never partial snippets that require assembly)
  • Use descriptive variable names (no single letters, no abbreviations)
  • Add comments explaining non-obvious logic
  • Keep files small and focused (under 200 lines)
  • Include error handling everywhere
  • Never use deprecated APIs
  • Never import external libraries without asking first

Planning

  • Before coding: generate a 5-10 step plan with file list, dependencies, and a manual test path
  • After coding: run the project, capture logs, and propose fixes if errors occur
  • Keep diffs small; commit every working increment with a clear message

Safety

  • Never delete files without asking first
  • Never deploy without explicit approval
  • Never commit secrets or API keys; use environment variables
  • Show what you will do before destructive operations
  • Create backups before modifying important files
  • If blocked for more than 10 minutes, switch approach or scaffold a simpler path

Output Format

For each task, return:

  1. Plan: What you will do and why
  2. Files: Which files will change or be created
  3. Commands: What to run (copy-paste ready)
  4. Test: How to verify it works (manual steps)
  5. Risks: What could go wrong and next steps
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 51 lines · 56 tokens per session scan A 34c1ba58ccb3

Subscribe to this mod's changes

non-coder-mode is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 471 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens