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 agentmods add instructions/jlifyio/wyx/claude-mdgit clone --depth 1 https://github.com/jlifyio/wyxWrote 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/instructions/jlifyio/wyx/claude-md)<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>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 | $0.04924 | $0.04924 |
| Opus 5 | $0.02462 | $0.02462 |
| Sonnet 5 | $0.00985 | $0.00985 |
| Haiku 4.5 | $0.00492 | $0.00492 |
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 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).
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.
- 3d ago First seen · 200 lines · 4,924 tokens per session scan B 5566866b1bcc
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.
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 AGENTS.md
Instructions for truecourse-ai/truecourse, covering truecourse — codex instructions, key files to keep updated, project layout, development commands and rules.
PhpCodeArcheology CLAUDE.md
Instructions for PhpCodeArcheology/PhpCodeArcheology, covering claude.md — phpcodearcheology, project overview, language, tech stack and project structure.
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.
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.
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.