meta-promote

meta-promote is a skill for Claude Code from laurigates/claude-plugins. It costs 41 tokens per session (2,306 once invoked), scanned D, original, MIT.

A workflow for deciding whether agent rules, skills, or helper definitions should remain in one project or be shared with a parent directory or user-wide configuration. It examines related configurations across sibling repositories.

In plain words
What is it for?
Use it to compare agent configuration across repositories, identify duplicate definitions, and promote genuinely shared ones to a parent or global scope.
Why use it?
It helps avoid maintaining the same rule in several places while preventing project-specific guidance from being shared too broadly.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Part of the agent-patterns-plugin plugin — 22 skills shipped together

Good fit Use it to compare agent configuration across repositories, identify duplicate definitions, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/laurigates/claude-plugins/meta-promote
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.

Any agent
npx skills add laurigates/claude-plugins --skill meta-promote
Clone the repo
git clone --depth 1 https://github.com/laurigates/claude-plugins

Made for: Claude Code.

Or install agent-patterns-plugin, the plugin that ships this one along with the rest of its 22 skills.

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 meta-promote

README.md
[![agentmods](https://agentmods.dev/badge/skills/laurigates/claude-plugins/meta-promote.svg)](https://agentmods.dev/skills/laurigates/claude-plugins/meta-promote)
Your own site
<a href="https://agentmods.dev/skills/laurigates/claude-plugins/meta-promote"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/meta-promote.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,306 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.02306
Opus 5 $0.00020 $0.01153
Sonnet 5 $0.00008 $0.00461
Haiku 4.5 $0.00004 $0.00231

Measured 7d ago against content hash 15748638f3a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade D, and why

meta-promote scanned grade D with 2 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 7d 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.

- Local `.claude/` tree: !`find . -path '*/.claude/*' -maxdepth 4 -type f -name '*.md' -not -path '*/node_modules/*' -not -path '*/.claude/worktrees/*'`

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| Use `rm -rf` on a scope's `.claude/` to "clean up" after promotion | Remove only the specific files you're promoting; leave the rest of the scope alone |
agent-patterns-plugin/skills/meta-promote/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

meta-promote

When to Use This Skill

Use this skill when... Use a different skill when...
Two or more sibling .claude/ scopes hold rules/skills/commands with the same name or topic, and you want to decide whether to lift them up to a shared parent You want to copy a project's config into your user-global config (use meta-assimilate)
A portfolio root (e.g. ~/repos/) has children whose configs overlap and you want to promote the common kernel You want to review existing agent configs for security and frontmatter completeness without changing scopes (use meta-audit)
You suspect a rule is duplicated across sibling repos and want a structured promotion / extraction / keep-scoped decision per file You want to author a brand-new skill from scratch (use custom-agent-definitions)

Context

  • Current directory: !pwd
  • Local .claude/ tree: !find . -path '*/.claude/*' -maxdepth 4 -type f -name '*.md' -not -path '*/node_modules/*' -not -path '*/.claude/worktrees/*'
  • Child .claude/ trees (one level down): !find . -mindepth 2 -maxdepth 4 -type d -name '.claude' -not -path '*/node_modules/*'

Parameters

Parse $ARGUMENTS:

  • scope-path (optional, default .) — the directory whose children's .claude/ trees should be evaluated for promotion up to this directory. The skill always treats scope-path as the target scope and its immediate .claude/-bearing children as the source scopes.

Your task

Execute this evaluation and (with approval) apply it. Do not promote anything without explicit per-candidate confirmation — promotion is a write to shared state and easy to get wrong.

1. Build the scope inventory

Walk three layers:

Layer Path Role
Target <scope-path>/.claude/{rules,skills,commands,agents}/ Where promoted files would land
Sources <scope-path>/*/.claude/{rules,skills,commands,agents}/ Children whose contents are candidates
Upstream User-global .claude/rules/ (resolve $HOME/.claude/rules during execution, not in the Context block) and any plugin skills already loaded for this session Already-covered material — promotion to the target would just duplicate this

Read the full file on GitHub · 141 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. 7d ago First seen · 141 lines · 41 tokens per session scan D 15748638f3a7

Subscribe to this mod's changes

meta-promote is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,306 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

extract-ssot

Deduplicate repeated markdown content, rule files, skill bodies, ADRs, docs, into a single named source of truth and migrate every call site to cite it by exact heading. Use when the same prose, literal, or concept appears (or is reworded) across files: 'DRY this prose', 'extract a shared rule', 'single source of…

melodic-software/claude-code-plugins · 130 tokens

feature-branch-pr-writing

Use this skill when the user asks to write, draft, create, or improve a PR description for a Shopware core repository PR — AND that PR targets a non-trunk feature branch (not trunk itself). Trigger phrases like "write a PR description", "draft the PR", "what should I put in the PR body". The skill detects the target…

shopwareLabs/ai-coding-tools · 152 tokens

ci-log-interpretation

Use this skill when reading or analyzing CI logs from a Shopware GitHub Actions workflow to figure out why a build failed — phrases like "why did CI fail", "what broke the build", "check the pipeline", "interpret these logs", "debug this red build" — or whenever raw run logs, job logs, or check annotations from a…

shopwareLabs/ai-coding-tools · 154 tokens

repo-activity

Scan all git repositories under /repos and report recent activity — last commit age, branch, uncommitted changes — in age-bucketed tables. Use when the user asks for a repo activity overview, "what have I been working on", portfolio status, or which repos are active/dormant.

laurigates/dotfiles · 65 tokens

a0-create-plugin

Create, extend, or modify Agent Zero plugins. Follows strict full-stack conventions (usr/plugins, plugin.yaml, Store Gating, AgentContext, plugin settings). Use for UI hooks, API handlers, lifecycle extensions, or plugin settings UI.

Gen-Verse/PAST-Bench · 54 tokens

a0-contribute-plugin

Guide for publishing an Agent Zero plugin to the community Plugin Index (a0-plugins repo). Covers GitHub repo setup, index.yaml creation, CI validation rules, and PR submission. Use when the user wants to share, publish, submit, or contribute a plugin to the Plugin Hub so other Agent Zero users can find and install it.

Gen-Verse/PAST-Bench · 74 tokens