wyx CLAUDE.md

wyx CLAUDE.md is an instructions file for coding agents from jlifyio/wyx. It costs 4,924 tokens per session, scanned B, original, MIT.

Repository instructions for Wyx, a Claude Code plugin that uses hooks to show architecture boundaries when code is edited near a module specification. A module specification is a document describing what a code module should do and where its boundaries are.

In plain words
What is it for?
Use them when developing Wyx, its specifications, architecture checks, or session, pre-tool, and post-tool hooks. They also describe how its skills and plugin files fit together.
Why use it?
They help the coding agent follow the project's architecture rules and reduce changes that cross module boundaries incorrectly. They also explain that Wyx is a plugin with hooks, rather than a standalone command-line program.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/jlifyio/wyx/claude-md
Clone the repo
git clone --depth 1 https://github.com/jlifyio/wyx

Wrote 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.

agentmods badge for wyx CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jlifyio/wyx/claude-md.svg)](https://agentmods.dev/instructions/jlifyio/wyx/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jlifyio/wyx/claude-md"><img src="https://agentmods.dev/badge/instructions/jlifyio/wyx/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,924 This file is loaded in full into every session.
When invoked 4,924 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.04924 $0.04924
Opus 5 $0.02462 $0.02462
Sonnet 5 $0.00985 $0.00985
Haiku 4.5 $0.00492 $0.00492

Measured 3d ago against content hash 5566866b1bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

wyx CLAUDE.md 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 3d 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.

**SessionStart** (command): Scans project for existing wyx artifacts (CONCEPT.md, PIPELINE.md, SYNCS.md) and reports coverage in sorted order. Warns if `jq` is missing. Suggests `/wyx:audit` if none found — but **only wh
CLAUDE.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 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.

Project Overview

wyx is a Claude Code plugin that provides architecture guardrails for LLM-assisted development. The core mechanism: when Claude writes code near a module with a spec, the PreToolUse hook automatically injects boundary declarations into Claude's context, reducing cross-module violations.

Adapts ideas from two sources:

  • WYSIWID (Meng & Jackson, MIT) — concept spec format and boundary declarations
  • WYWIWID (Dr. Ernie) — evidence-based legibility concepts (concept drift detection, pipeline invariants)

This is a Claude Code plugin (5 SKILL.md files + 3 hooks), not a CLI tool or runtime engine. The primary differentiator is the hooks — the skills are convenience packaging for generating the specs that fuel the hooks.

Architecture

.claude-plugin/
├── plugin.json             # Plugin manifest (name: "wyx")
hooks/
└── hooks.json              # SessionStart + PreToolUse + PostToolUse hooks (command type only)
scripts/
├── session-start.sh        # Artifact coverage + drift/ARCHITECTURE.md staleness + uncovered modules (with exclusions)
├── drift-context.sh        # Boundary injection near specs + CRLF handling + shadowing mitigation
└── post-check.sh           # Post-edit dependency list reinforcement (silent when no spec/deps)
skills/
├── audit/SKILL.md          # /wyx:audit — project audit & command planner
├── concept/SKILL.md        # /wyx:concept — bounded concept design + drift detection
├── map/SKILL.md            # /wyx:map — architecture visualization from specs
├── pipeline/SKILL.md       # /wyx:pipeline — data pipeline specs with quality invariants
└── sync/SKILL.md           # /wyx:sync — sync coordination maps

Skills

Each skill is fully described in its own SKILL.md; CLAUDE.md keeps only one-line invocation summaries. For Five Design Rules, drift calibration, retrofit guidance, and per-skill internals, read skills/<name>/SKILL.md (and skills/<name>/references/ where present).

Read the full file on GitHub · 200 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. 3d ago First seen · 200 lines · 4,924 tokens per session scan B 5566866b1bcc

Subscribe to this mod's changes

wyx CLAUDE.md is an instructions file published in the GitHub repository jlifyio/wyx (3 stars, last pushed 25d ago), licensed MIT. It adds 4,924 tokens to every session, about $0.0246 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.

Related

Other instructions, from other repositories

truecourse CLAUDE.md

Instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.

truecourse-ai/truecourse · 5,107 tokens

truecourse AGENTS.md

Instructions for truecourse-ai/truecourse, covering truecourse — codex instructions, key files to keep updated, project layout, development commands and rules.

truecourse-ai/truecourse · 689 tokens

PhpCodeArcheology CLAUDE.md

Instructions for PhpCodeArcheology/PhpCodeArcheology, covering claude.md — phpcodearcheology, project overview, language, tech stack and project structure.

PhpCodeArcheology/PhpCodeArcheology · 976 tokens

drift copilot-instructions.md

Instructions for mick-gsk/drift, covering drift — verbindliche arbeitsgrundlage für alle agenten, primärmodus bei prompt-engineering, zuerst das richtige primitive wählen, nicht verhandelbare schärferegeln and mindestvertrag für jeden guten prompt.

mick-gsk/drift · 3,275 tokens

drift drift-push-gates.instructions.md

Nutze diese Instruction, wenn ein Commit, ein Push oder eine Release-Vorbereitung im Drift-Repo ansteht. Sie ist die autoritative Gate-Quelle fuer Pre-Push-Anforderungen, Bypaesse und lokale CI-Pflichten.

mick-gsk/drift · 2,980 tokens

drift drift-quality-workflow.instructions.md

Nutze diese Instruction bei nicht-trivialen Aenderungen, Reviews oder Fix-Loops im Drift-Repo. Fokus: adversarialer Gegenreview, iterativer Fix-Loop, expliziter Freigabestatus und Human-in-the-Loop vor Merge.

mick-gsk/drift · 1,887 tokens