settings-schema

A command for extracting the settings rules used by Claude Code, the command-line coding assistant, from its installed package. It turns those rules into documentation and comparisons.

In plain words
What is it for?
Use it to document a Claude Code version, compare settings across versions, or find settings absent from the official SchemaStore reference.
Why use it?
It helps reveal which settings exist, which are missing from public documentation, and how settings changed between versions.

Command

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/bengous/claude-code-plugins/settings-schema
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 $0.00007 $0.00738
Opus 5 $0.00003 $0.00369
Sonnet 5 $0.00001 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured yesterday against content hash efedbed37bc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

settings-schema 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-settings-manager/commands/settings-schema.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Settings Schema Extraction

You are extracting and analyzing Claude Code's settings schema from the npm package bundle.

Background

Claude Code's settings are validated using Zod schemas. These schemas contain .describe() strings that document each setting. This command extracts those descriptions from the minified cli.js bundle to:

  1. Generate documentation for all available settings
  2. Find undocumented settings not in the official schemastore.org schema
  3. Compare schemas between versions

Your Task

Step 1: Determine What the User Wants

If the user hasn't specified, ask what they want to do:

Use AskUserQuestion:
Question: "What would you like to do with the Claude Code schema?"
Options:
- "Extract schema from current/specific version (generate docs)"
- "Compare versions (find new/removed settings)"
- "Find undocumented settings (diff against schemastore.org)"

Step 2: Get Version Information

Check the current Claude Code version:

claude --version

If user wants a specific version, they can provide it. Otherwise use "latest".

Step 3: Execute the Appropriate Command

For schema extraction:

"${CLAUDE_PLUGIN_ROOT}/scripts/settings-manager" schema-extract \
  --version <VERSION> \
  --output-dir <OUTPUT_DIR> \
  --format both

Default output directory: current directory or user-specified.

For version comparison:

"${CLAUDE_PLUGIN_ROOT}/scripts/settings-manager" schema-diff \
  --base <VERSION1> \
  --compare <VERSION2>

For finding undocumented settings:

"${CLAUDE_PLUGIN_ROOT}/scripts/settings-manager" schema-diff \
  --base schemastore \
  --compare latest

Step 4: Present Results

After extraction, read and summarize the generated files:

  1. For extraction: Show a summary of what was extracted:

    • Total describe strings found
    • Property mappings discovered
    • File locations
  2. For comparison: Highlight:

    • New settings in the compared version
    • Removed settings
    • New describe strings

Read the full file on GitHub · 119 lines

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 · 119 lines · 7 tokens per session scan A efedbed37bc6

Subscribe to this mod's changes

settings-schema is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 738 once invoked, about $0.0000 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.