coding-level

A command that sets how deeply Claude explains coding work, from beginner-friendly explanations to brief, code-focused responses. The setting applies to the current session or project.

In plain words
What is it for?
Choosing an explanation level, viewing the available levels, resetting the setting, and controlling how Claude structures coding answers.
Why use it?
It prevents explanations from being too basic or too advanced for the person reading them.

Command for Claude Code

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 commands/huuanh20/awesome-ai-agent-skills/coding-level
Clone the repo
git clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skills

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 472 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 $0.00024 $0.00472
Opus 5 $0.00012 $0.00236
Sonnet 5 $0.00005 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured yesterday against content hash b304485d5fab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-level 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 yesterday.

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.

.claude/commands/ck/coding-level.md · 46 lines

What it actually says

Set the coding explanation depth. Levels control how Claude structures and explains responses.

Levels

# Name Style
-1 Default Claude's built-in style — no injection, no overrides
0 ELI5 No assumed knowledge — real-world analogies, every term explained
1 Junior Explains WHY, mentor tone, names patterns, flags pitfalls
2 Mid-level Design patterns, system thinking, recommendation-first
3 Senior Trade-offs and architecture first, terse, no hand-holding
4 Tech Lead Risk analysis, business impact, no implementation detail
5 God Mode Code-first, zero ceremony, peer-level (default when no level set)

Usage

/ck:coding-level          # show current level + interactive menu
/ck:coding-level -1       # use Claude's default style (no injection)
/ck:coding-level 3        # set to Senior
/ck:coding-level reset    # remove config entirely (same as -1 but clears the key)

How to execute this command

Read the argument $ARGUMENTS:

No argument — read .ck.json at the project root (default: 5 if not set), print the level table above, and ask the user to pick a number -1 through 5.

Argument is a number -1 through 5 — write .ck.json at the project root:

{ "codingLevel": <N> }

Confirm with one line: Coding level set to <N> (<Name>). Takes effect next session.

Argument is reset — remove the codingLevel key from .ck.json if it exists (keep other keys intact). Confirm: Coding level reset. Claude's default style will be used.

Argument is anything else — print usage and the level table.

The file lives at the project root as .ck.json. Do NOT write to ~/.claude/ or .claude/.

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. yesterday First seen · 46 lines · 24 tokens per session scan A b304485d5fab

Subscribe to this mod's changes

coding-level is a command published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 472 once invoked, about $0.0001 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.