agentmods.dev

skill-heaven

skill-heaven is a plugin for Claude Code from gaia-research/gaia-skill-heaven. Its manifest loads nothing; the 5 skills, 5 commands, 1 MCP server it bundles cost 211 tokens per session together, scanned A, original, MIT.

A prototype for bringing one Claude Code skill into the current session without installing it permanently. Claude Code is a coding assistant that works with a software repository.

In plain words
What is it for?
Use its `/summon` command to add one skill to a Claude Code session and choose the requested context level.
Why use it?
It lets a session use a selected skill temporarily while keeping the local installation unchanged.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 4repo changed 21d ago A scan tokens not measured original MIT

Good fit Use its /summon command to add one skill to a Claude Code session and choose the requested context level.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add gaia-research/gaia-skill-heaven
/plugin install skill-heaven
View source ↗ gaia-research/gaia-skill-heaven gaia-research.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/gaia-research/gaia-skill-heaven

Made for: Claude Code.

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 skill-heaven

README.md
[![agentmods](https://agentmods.dev/badge/plugins/gaia-research/gaia-skill-heaven/skill-heaven/github.svg)](https://agentmods.dev/plugins/gaia-research/gaia-skill-heaven/skill-heaven)
Your own site
<a href="https://agentmods.dev/plugins/gaia-research/gaia-skill-heaven/skill-heaven"><img src="https://agentmods.dev/badge/plugins/gaia-research/gaia-skill-heaven/skill-heaven/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-heaven

Your own site · 80×15
<a href="https://agentmods.dev/plugins/gaia-research/gaia-skill-heaven/skill-heaven"><img src="https://agentmods.dev/badge/plugins/gaia-research/gaia-skill-heaven/skill-heaven.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 5 skills, 5 commands, 1 MCP server cost 211 tokens a session between them.
Security scan A 0 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.
Security

Grade A, and why

skill-heaven 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 21d 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.

plugins/skill-heaven/.claude-plugin/plugin.json · 42 lines

What it actually says

{
  "name": "skill-heaven",
  "displayName": "Skill Heaven",
  "version": "0.1.2",
  "description": "Skill Heaven is live. Summon one skill into a session with nothing installed: manual /summon at every rung, a clean-room launcher floor (/skill-zero), converge and explore bands over one relevance-ranked summon (/skill-heaven, /skill-hell), and the crown rung (/skill-ultra), from a Skill Tree or a flat GitHub repository. Its output is reference data, never standing authority; what each rung means in behaviour is still provisional.",
  "homepage": "https://github.com/gaia-research/gaia-skill-heaven#readme",
  "repository": "https://github.com/gaia-research/gaia-skill-heaven",
  "license": "MIT",
  "keywords": [
    "skills",
    "context",
    "context-management",
    "context-bloat",
    "on-demand",
    "ephemeral-skills",
    "dynamic-skills",
    "agent-skills",
    "summon",
    "clean-launch",
    "skill-heaven",
    "skill-hell",
    "gaia"
  ],
  "author": {
    "name": "Gaia Research"
  },
  "userConfig": {
    "skill_url": {
      "type": "string",
      "title": "Skill URL",
      "description": "One source URL. Use a Skill Tree website root such as https://gaiaskilltree.com or a flat GitHub repository containing SKILL.md files.",
      "default": "https://gaiaskilltree.com"
    },
    "zero_cuts": {
      "type": "string",
      "title": "Zero cuts (temporary/all) skills. Default is temporary.",
      "description": "\"temporary\" (default) cuts temporary automatic summons while manual /summon remains available. \"all\" cuts all skill summons, including manual /summon.",
      "default": "temporary"
    }
  }
}
Contents

What it installs

The manifest is a name and a version. 5 skills, 5 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 211 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 21d ago Changed · +7 lines 881bc29c0eae
  2. 1mo ago Changed 079242b27cbf
  3. 1mo ago First seen · 35 lines scan A 94cd8aef019d

Subscribe to this mod's changes

skill-heaven is a plugin published in the GitHub repository gaia-research/gaia-skill-heaven (4 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Building agentsClaude Codeagentagent-skillsagentic-workflowclaude-code-pluginclaude-skills
Related

Other plugins, from other repositories

lattice

Composable AI skills framework covering the full software delivery lifecycle — design, architecture, implementation, testing, and review.

techygarg/lattice · not measured

team-of-agents

A Claude Code plugin providing a full SDLC team of specialised AI agents with an orchestrator that plans tasks and dispatches specialist subagents: a composable frontend trio (planner, engineer, reviewer) with domain and stack overlays, backend engineer, Kotlin engineer, data analyst, UX researcher, senior engineer…

pranav8494/team-of-agents · not measured

loop-kit

A session-based working method for coding agents: plan an epic into thin complete slices, build one at a time, verify by observing real behaviour, and hand off so the next session starts where the last one stopped.

cbdreamer11/CB-loop-kit-claude-plugin · not measured

agent-mesh

Cross-session expert queries between local AI coding agents.

mertbarutcuoglu/agent-mesh · not measured

ank

ANK Skills — small, composable Claude Code skills for an agentic engineering workflow.

ananthanandanan/skills · not measured

foundry-research

Deep research agent with academic database search, structured source management, and multi-agent synthesis. Produces evidence-backed research reports.

foundry-works/foundry-research · not measured