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.
git clone --depth 1 https://github.com/gaia-research/gaia-skill-heavenWrote 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/plugins/gaia-research/gaia-skill-heaven/skill-heaven)<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.
<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>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 10d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 — 207 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill summon A 23 tokens
- Skill skill-ultra A 24 tokens
- Skill skill-heaven A 27 tokens
- Skill skill-hell A 31 tokens
- Skill skill-zero A 23 tokens
- Command skill-ultra A 16 tokens
- Command summon A 14 tokens
- Command skill-heaven A 16 tokens
- Command skill-hell A 18 tokens
- Command skill-zero A 15 tokens
- MCP server skill-summon A not measured
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.
- 10d ago First seen · 35 lines scan A 94cd8aef019d
skill-heaven is a plugin published in the GitHub repository gaia-research/gaia-skill-heaven (4 stars, last pushed today), with no licence file. 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.
Other plugins, from other repositories
lattice
Composable AI skills framework covering the full software delivery lifecycle — design, architecture, implementation, testing, and review.
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, frontend designer, backend engineer, Kotlin engineer, data analyst, UX researcher, senior engineer, DevEx, product manager, project manager, QA engineer, document writer…
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.
agent-mesh
Cross-session expert queries between local AI coding agents.
ank
ANK Skills — small, composable Claude Code skills for an agentic engineering workflow.
foundry-research
Deep research agent with academic database search, structured source management, and multi-agent synthesis. Produces evidence-backed research reports.