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/ash1794/vibe-engineering/claude-mdgit clone --depth 1 https://github.com/ash1794/vibe-engineeringWrote 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/ash1794/vibe-engineering/claude-md)<a href="https://agentmods.dev/instructions/ash1794/vibe-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/ash1794/vibe-engineering/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 | $0.00899 | $0.00899 |
| Opus 5 | $0.00449 | $0.00449 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
vibe-engineering 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project notes for Claude Code (and any other AI agent) working in this repo.
What this repo is
A Claude Code marketplace (vibe-plugins) that ships one plugin (vibe-engineering) containing 38 engineering-discipline skills. The same SKILL.md files also power OpenAI Codex via .agents/skills/.
vibe-engineering/ # repo root = marketplace root
├── .claude-plugin/
│ └── marketplace.json # marketplace: "vibe-plugins"
├── plugins/
│ └── vibe-engineering/ # plugin root
│ ├── .claude-plugin/plugin.json # plugin: "vibe-engineering"
│ └── skills/ # 38 SKILL.md files
└── .agents/skills -> ../plugins/vibe-engineering/skills # Codex
Install flow users follow:
/plugin marketplace add ash1794/vibe-engineering
/plugin install vibe-engineering@vibe-plugins
Plugin structure invariants — DO NOT BREAK THESE
These three rules are non-negotiable. Breaking any one produces either an uninstallable repo or a recursive plugin-cache loop (issue #1). scripts/validate-skills.sh enforces all three in CI — the build will fail if you violate them.
1. .claude-plugin/marketplace.json MUST exist at the repo root
Without it, /plugin marketplace add has nothing to catalog. The repo becomes uninstallable via any supported Claude Code flow. The claude plugin add github:... command advertised in older docs does not exist.
History: commit 50e13ad deleted marketplace.json to work around the recursion bug below. It made the plugin uninstallable for a full release cycle. Don't repeat this.
2. The plugin directory MUST NOT be the repo root
The plugin must live in a subdirectory (we use plugins/vibe-engineering/), not alongside marketplace.json. If plugin.json sits next to marketplace.json, Claude Code's plugin cache copies the entire repo — including marketplace.json — into ~/.claude/plugins/cache/<marketplace>/<plugin>/. The cached plugin directory then also looks like a marketplace, Claude Code re-enumerates it, and you get cache/.../cache/... recursion until ENAMETOOLONG.
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.
- 5d ago First seen · 66 lines · 899 tokens per session scan A cc81d5eca042
vibe-engineering CLAUDE.md is an instructions file published in the GitHub repository ash1794/vibe-engineering (10 stars, last pushed 3mo ago), licensed MIT. It adds 899 tokens to every session, about $0.0045 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.
Other instructions, from other repositories
cherry-studio AGENTS.md
AGENTS.md instructions for CherryHQ/cherry-studio, a project described as: AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.
ark-space CLAUDE.md
Instructions for arch3rPro/ark-space, covering claude code guidance, start here, repository rules, validation and release boundary.
erpaval CLAUDE.md
Instructions for theagenticguy/erpaval, covering erpaval-plugin, repo structure, version management, tools and hooks.
wtcraft CLAUDE.md
Instructions for zywkloo/wtcraft, covering wtcraft routing, repo structure (wtcraft dogfooding), model knowledge policy and release guardrails.
hplan CLAUDE.md
Instructions for kimsanguine/hplan, covering claude.md — hplan project rules (adk l1: memory), hplan context, 9 behavioral rules, rule 1 — think before coding and rule 2 — simplicity first.
ed3d-plugins CLAUDE.md
Claude Code instructions for ed3dai/ed3d-plugins, covering ed3d-plugins, conventions, task invocations use xml syntax and version updates require marketplace and changelog sync.