agentmods.dev

wsc CLAUDE.md

Project-specific instructions for the WSC codebase, including its web app, MCP server, command-line tool, architecture, and development commands. WSC is a writing checker that detects issues such as passive voice, repeated words, and overly long sentences.

In plain words
What is it for?
Use them when developing the Svelte web editor, HTTP API, MCP interfaces, command-line checker, or GitHub Action, or when running focused tests and production builds.
Why use it?
They explain how the separate parts of the project are built, tested, and checked. This helps an agent change the right package and run the appropriate verification commands.

Instructions file

5 1mo ago A scan 1,661 tokens original MIT
View the source file theserverlessdev/wsc
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 instructions/theserverlessdev/wsc/claude-md
Clone the repo
git clone --depth 1 https://github.com/theserverlessdev/wsc
Per session 1,661 This file is loaded in full into every session.
When invoked 1,661 The same file — it is already loaded in full.
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 $0.01661 $0.01661
Opus 5 $0.00830 $0.00830
Sonnet 5 $0.00332 $0.00332
Haiku 4.5 $0.00166 $0.00166

Measured 2d ago against content hash 5eac4b962272, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wsc CLAUDE.md 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm run dev          # Start dev server at localhost:5173
npm run build        # Build for production (Cloudflare Workers)
npm run check        # Type check (svelte-kit sync + svelte-check)
npm test             # Run all tests (vitest run)
npm run test:watch   # Run tests in watch mode
npm run test:coverage # Coverage report (istanbul)

Run a single test file: npx vitest run tests/core/detector.test.ts

MCP Server (separate package in mcp-server/)

cd mcp-server && npm ci && npm run build   # Build standalone MCP server

CLI (separate package in cli/)

cd cli && npm ci && npm run build   # Build CLI
node cli/dist/cli/index.js check "**/*.md"  # Run check

Architecture

Writing Style Checker (WSC) — detects 8 types of writing issues. Six interfaces: web editor, HTTP API, remote MCP, local MCP, CLI, and GitHub Action.

Core Detection Engine (src/core/)

  • detector.ts — 8 detector functions: detectWeaselWords, detectPassiveVoice, detectDuplicateWords, detectLongSentences, detectNominalizations, detectHedging, detectAdverbs, detectAiTells, plus removeDuplicateWord. All return match positions (index + length). Weasel words, nominalizations, hedging, adverbs, and AI tells accept optional custom word lists for config support.
  • words.ts — Word lists: 95 weasel words (allWeaselWords), 260 irregular verbs, 13 auxiliary verbs, 245 nominalizations (with suggestions), 100 hedging phrases, 139 filler adverbs, 99 abbreviations, 98 AI tells vocabulary entries (with optional inflected variants and reasons), 83 AI tells phrases (with reasons), 12 AI tells structural regex patterns (aiTellsPatterns, named + removable via config removePatterns).
  • config.ts — Browser-safe config types (WscConfig), DEFAULT_CONFIG, mergeConfig(), applyWordListOverrides(), applyNominalizationOverrides(), validateConfig(). No Node.js imports.
  • config-node.ts — Node-only: loadConfigFromFile(), findConfigFile(). Uses node:fs/promises and node:path. Only imported by mcp-server and CLI.
  • markdown.ts — maskMarkdown() blanks non-prose Markdown regions (fenced code, inline code spans, tables, headings, HTML comments) while preserving length and line layout, so offsets still map back to the original text. isMarkdownFile() checks a path's extension.
  • analyzer.ts — analyzeText(text, config?, options?: AnalyzeOptions) — the single entry point all consumers call. AnalyzeOptions.markdown runs the text through maskMarkdown() before detection. Runs enabled detectors with config overrides, returns AnalysisResult.
  • index.ts — Public re-exports (does NOT export config-node functions).

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 1,661 tokens per session scan A 5eac4b962272

Subscribe to this mod's changes

wsc CLAUDE.md is an instructions file published in the GitHub repository theserverlessdev/wsc (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,661 tokens to every session, about $0.0083 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.

Backend and APIsFrontendTestingai-detectionai-slopcloudflarecloudflare-pagescloudflare-workerssveltekit
Related

Other instructions, from other repositories

cld-flare-maxxing AGENTS.md

Instructions for AbhiiGatty/cld-flare-maxxing, covering cld-flare-maxxing — operating contract, what this is, golden rules, vocabulary: what "deploy it" (and similar) actually means and confirming a deploy landed.

AbhiiGatty/cld-flare-maxxing · 3,101 tokens

cld-flare-maxxing CLAUDE.md

Instructions for AbhiiGatty/cld-flare-maxxing, covering claude code layer, what claude code discovers here, optional mcp access, no website side effects and communication style: simplified technical english.

AbhiiGatty/cld-flare-maxxing · 579 tokens

cld-flare-maxxing copilot-instructions.md

Instructions for AbhiiGatty/cld-flare-maxxing: Read AGENTS.md at the repo root before doing any work here. It's the full operating contract: read-only by default, break-glass for any mutation, dry-run first.

AbhiiGatty/cld-flare-maxxing · 39 tokens

supermemory CLAUDE.md

Claude Code instructions for supermemoryai/supermemory, covering claude.md, repository structure, applications (apps/), development commands and root level (monorepo).

supermemoryai/supermemory · 884 tokens

mcp AGENTS.md

Instructions for cloudflare/mcp, covering agents.md, project overview, mcp specification compliance, repository structure and setup.

cloudflare/mcp · 3,207 tokens

cloudflare-workers-nextjs-saas-template AGENTS.md

Instructions for LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, covering project context, vinext, general coding rules, control flow and comments.

LubomirGeorgiev/cloudflare-workers-nextjs-saas-template · 5,209 tokens