publish-copy

A rule that defines which plugin files may be copied to a publishing repository and which internal files must be left out.

In plain words
What is it for?
Use it when running the publish-copy process to copy approved manifests, skills, agents, commands, and documentation.
Why use it?
It prevents accidental publication of private tooling or unrelated files while ensuring the required plugin components are included.

Cursor rule

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 rules/wake-engineering/ai-plugin/publish-copy
Clone the repo
git clone --depth 1 https://github.com/wake-engineering/ai-plugin
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00037 $0.00588
Opus 5 $0.00018 $0.00294
Sonnet 5 $0.00007 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured yesterday against content hash 800f0586911c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

publish-copy 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 yesterday.

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.

tooling/rules/publish-copy.mdc · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish-Copy Rule

When copying plugin artifacts to the publish repository, follow this rule.

Inclusion (COPY ONLY these paths)

Copy these paths from toolkit repo root to publish destination. Overwrite existing files.

Path Description
.cursor-plugin/ Cursor manifest and plugin metadata
.claude-plugin/ Claude/Agent Plugins manifest
.mcp.json MCP server definitions (Chrome DevTools only)
skills/ Skills (wake-storefront-api, wake-checkout-flow, wake-product-variants, wake-storefront-reference-patterns, wake-hotsite-banners, web-performance-audit, and spec-derived only)
agents/ Agents (wake-storefront-developer, wake-checkout-architect, wake-migration-specialist, wake-security-auditor, wake-qa-expert, wake-performance-engineer, wake-graphql-architect, wake-code-reviewer, and spec-derived only)
commands/ Commands (wake-product-page, wake-search-page, wake-checkout-flow, wake-migrate-storefront-query, wake-security-audit, wake-test-plan, wake-performance-review, wake-query-review, wake-code-review, and spec-derived only)
README-publish.md Plugin README (copied as README.md; toolkit-only content excluded)
assets/ Logo and other marketplace assets
scripts/ Plugin utility scripts (wake-graphql-validate, wake-query-from-reference, wake-checkout-flow-validator)

Exclusion (NEVER copy)

Do NOT copy any of the following:

  • tooling/ — Internal maintainer tooling (this rule and the publish-copy command live here)
  • rules/ — Toolkit-only rules directory (no marketplace-facing rules at this time)
  • .bmad-core/ — Internal BMad tooling
  • .codex/ — Internal Codex tooling
  • .specify/ — Speckit workflow and memory
  • specs/ — Feature specs (toolkit-only)
  • .publish-config.json — Local config (may contain absolute paths)
  • Any agents, skills, tools, or workflows NOT created via specs
  • node_modules/, dist/, build/, .git/, *.log, .env*

Behavior

  • Overwrite: Replace existing files at destination with toolkit copies
  • Create destination: If destination path does not exist, create it
  • Report empty: If no spec-derived artifacts exist to copy, report and exit

Read the full file on GitHub · 45 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. yesterday First seen · 45 lines · 37 tokens per session scan A 800f0586911c

Subscribe to this mod's changes

publish-copy is a cursor rule published in the GitHub repository wake-engineering/ai-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 588 once invoked, about $0.0002 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.