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/wigtn/wigtn-plugins/claude-mdgit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWrote 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/wigtn/wigtn-plugins/claude-md)<a href="https://agentmods.dev/instructions/wigtn/wigtn-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/wigtn/wigtn-plugins/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 | $0.02548 | $0.02548 |
| Opus 5 | $0.01274 | $0.01274 |
| Sonnet 5 | $0.00510 | $0.00510 |
| Haiku 4.5 | $0.00255 | $0.00255 |
Grade A, and why
wigtn-plugins 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WIGTN Claude Code Plugin Tools
Project Overview
A unified Claude Code plugin enabling AI-powered Vibe Coding: idea to production with minimal friction.
Version: 0.1.16 License: Apache-2.0 Repository: https://github.com/wigtn/wigtn-plugins
Architecture
wigtn-plugins/
├── .claude-plugin/ # Marketplace metadata
├── plugins/
│ └── wigtn-plugins/ # Unified plugin: 11 agents, 5 commands, 7 skills, 20 design styles
│ ├── .claude-plugin/ # Plugin metadata
│ ├── agents/ # 11 agent definitions
│ ├── commands/ # 5 commands (/prd, /screen-spec, /implement, /auto-commit, /review-pr)
│ ├── skills/ # 7 skills (code-review-levels, design-system-reference, handdrawn-diagram, screen-spec, team-memory-protocol, wigtn-ppt)
│ └── hooks/ # Hooks configuration
├── CLAUDE.md # This file
├── README.md # English docs
└── README.ko.md # Korean docs
Plugin Structure
plugins/wigtn-plugins/
├── .claude-plugin/plugin.json # Plugin metadata
├── agents/ # Agent definitions (.md)
├── commands/ # User-invocable commands (.md)
├── skills/ # Skills with SKILL.md + reference files
└── hooks/hooks.json # Hooks configuration
Pipeline Flow
/prd <feature>
→ PRD.md + PLAN_{feature}.md (§2.3 User Roles, §5.4 Pages, §5.4.1 State Matrix, §5.5 User Flow 포함)
→ digging (`prd-reviewer`: 4-lens 적대적 분석 + completeness-critic; 조건부 external-grounding)
→ /screen-spec <feature> (FE 페이지가 있을 때만; IA / Flow / Spec / Wireframe / Handoff 5종 생성)
→ /implement (triage → quick-fix: 경량 단일 에이전트 | feature/greenfield: DESIGN → BUILD
→ [Frontend? → design-discovery → style select]
→ [Linear 연동? → Epic/하위 이슈 등록 → 이슈 단위 순차 BUILD | 미연동? → BUILD team parallel])
→ /auto-commit (변경 규모에 비례한 리뷰 → findings 롤업 게이트 → commit)
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 · 137 lines · 2,548 tokens per session scan A bd4209ad6eea
wigtn-plugins CLAUDE.md is an instructions file published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 17d ago), licensed Apache-2.0. It adds 2,548 tokens to every session, about $0.0127 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 2026-08-30.
Other instructions, from other repositories
open-ontologies CLAUDE.md
Instructions for fabio-rovai/open-ontologies, covering open ontologies, ontology engineering workflow, generate, validate and load and reason.
knowns GEMINI.md
Instructions for knowns-dev/knowns, covering gemini, canonical guidance, minimum rules and quick reference.
kin GEMINI.md
Instructions for firelock-ai/kin, covering kin: read the repository from the graph, pick the tool by what you know, trust the envelope, not the emptiness, if the tools have no graph and a working order.
kin AGENTS.md
Instructions for firelock-ai/kin, covering agents.md and this repo's role.
AINativeOS CLAUDE.md
Claude Code instructions for impactbrussels/AINativeOS, covering ai-native os: master instructions, what ai-native os is, the journey (primary organising axis), how the pieces fit and operating principles (enforce these in every interaction).
AINativeOS GEMINI.md
Gemini CLI instructions for impactbrussels/AINativeOS, covering ai-native os: agent instructions (gemini cli mirror), what this is, operating principles (enforce every time), learning loop and tooling & attribution.