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.
npx skills add sleeyax/promptfiles --skill claude-settingsgit clone --depth 1 https://github.com/sleeyax/promptfilesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sleeyax/promptfiles/claude-settings)<a href="https://agentmods.dev/skills/sleeyax/promptfiles/claude-settings"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/claude-settings.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.02309 |
| Opus 5 | $0.00023 | $0.01154 |
| Sonnet 5 | $0.00009 | $0.00462 |
| Haiku 4.5 | $0.00005 | $0.00231 |
Grade B, and why
claude-settings scanned grade B with 1 finding 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
description: Toggle token-hungry Claude Code features (bundled skills, workflows, artifacts, hooks, auto memory, built-in tools, ...) on or off via ~/.claude/settings.json to shrink the system prompt. 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.
Claude Settings
Show which token-saving levers are currently on or off in the user-level Claude Code settings, let the user flip any of them, and apply the change safely. This is a toggle, not an install: it is safe to re-run any time to flip features back.
Hard rules
- Never write without an explicit user choice. Use the
AskUserQuestiontool when it's available in the session; where it isn't, ask in plain text with the same numbered options and stop until the user replies. Selecting nothing means writing nothing. - Merge, never rewrite. The settings file holds unrelated keys (
model,enabledPlugins,tui, ...). Only set or delete the exact keys the user chose, via jq. Never emit a hand-built full file. - Leave scoped permission rules alone. Only bare tool names in
permissions.deny(e.g."NotebookEdit") remove the tool's definition from the prompt payload. Entries containing(— e.g."Bash(rm *)"— are scoped rules: they block execution but save zero tokens. Never add, remove, or reorder them, and never offer them as toggles. - jq is required. If
command -v jqfails, stop and tell the user to install it. Never fall back to editing the JSON by hand or with sed. - User-level file only. The target is
${CLAUDE_CONFIG_DIR:-$HOME/.claude}/settings.json. Do not touch project.claude/settings.jsonfiles even if present. - Walk through everything, every run. The walkthrough has two mandatory halves: the feature flags (step 3a) and the built-in tools catalog (step 3b). Never end the asking phase after the feature flags alone — 3b runs even if the user selected nothing in 3a.
Feature catalog
A feature is ON when its key is absent from the settings file or set to any value other than the "value when OFF" below. To turn a feature back ON, delete the key (restores the default and keeps the file minimal) rather than writing the opposite value, unless the user explicitly wants it pinned.
| Feature | Settings key | Value when OFF | Token impact | What you lose when OFF |
|---|---|---|---|---|
| Bundled skills catalog | disableBundledSkills |
true |
Large | Built-in skills catalogue in the system prompt |
| Workflows | disableWorkflows |
true |
Large | Workflow tool and workflow commands |
| Artifacts | disableArtifact |
true |
Medium | Artifact tool (publishing to claude.ai) |
| Background agents | disableAgentView |
true |
Medium | claude agents, /background, supervisor |
| claude.ai connectors | disableClaudeAiConnectors |
true |
Medium | Auto-fetched claude.ai MCP connectors |
| Remote control | disableRemoteControl |
true |
Small | Controlling the session remotely |
| Hooks + status line | disableAllHooks |
true |
Varies | ALL hooks and the custom status line |
| Auto memory | autoMemoryEnabled |
false |
Medium | Automatic memory across sessions |
| File checkpointing | fileCheckpointingEnabled |
false |
Small | File snapshots for /rewind |
| Auto-compact | autoCompactEnabled |
false |
Small | Automatic compaction; caution: hitting the context limit then ends the session, which may cost more than it saves |
| Away summaries | awaySummaryEnabled |
false |
Small | Session recap after returning from absence |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 119 lines · 46 tokens per session scan B 19b528c32fce
claude-settings is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 2,309 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…