What is gaia-meta-sweep?

A registry-wide audit coordinator for Gaia, a catalogue of skills and related items. It checks every skill through multiple review agents and produces an HTML report.

Use it for systemic analysis, adversarial verification, finding candidates for combined skills, and proposing general skill references.

It helps reveal broad problems and possible gaps across the whole registry instead of checking entries one by one.

gaia-meta-sweep — Skill for Claude Code and Codex by gaia-research

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 gaia-research/gaia-skill-tree --skill gaia-meta-sweep

Clone the repo

git clone --depth 1 https://github.com/gaia-research/gaia-skill-tree

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gaia-research/gaia-skill-tree/gaia-meta-sweep/github.svg)](https://agentmods.dev/skills/gaia-research/gaia-skill-tree/gaia-meta-sweep)

Your own site

<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-tree/gaia-meta-sweep"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-tree/gaia-meta-sweep/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-tree/gaia-meta-sweep"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-tree/gaia-meta-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,955 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00137	$0.05955
Opus 5.5	$0.00055	$0.02382
Sonnet 5.5	$0.00027	$0.01191
Haiku 4.5	$0.00014	$0.00596

Measured 9d ago against content hash 2443e0e71f22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gaia-meta-sweep 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 9d 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.

.agents/skills/gaia-meta-sweep/SKILL.md · 350 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

9d ago Changed 2443e0e71f22
16d ago Changed · +10 tokens per session 2f5aff0959f6
19d ago Changed · +2 lines 1b50c9e2a6b1
20d ago Changed · +82 lines · -95 tokens per session e63fd75a4482
1mo ago Changed · +13 lines 41fd09ba7603
2mo ago Changed · +1 lines · +13 tokens per session b04e9cf3135f
2mo ago Changed 67114ae375be
2mo ago First seen · 252 lines · 209 tokens per session scan A 6b335921ccf9

Subscribe to this mod's changes

gaia-meta-sweep is a skill published in the GitHub repository gaia-research/gaia-skill-tree (22 stars, last pushed today), with no licence file. It adds 137 tokens to every session and 5,955 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.

Building agents LLM agent-tools ai ai-agent claude knowledge-graph

gaia-meta-sweep next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gaia-meta-sweepgaia-research/gaia-skill-tree	Skill	22	today	none	A	137	Claude Code, Codex
data-science-analysisagentscope-ai/QwenPaw-Data	Skill	196	7d ago	Apache-2.0	A	237	Claude Code, Codex
bi-clusteringagentscope-ai/QwenPaw-Data	Skill	196	7d ago	Apache-2.0	A	107	Claude Code, Codex
bi-attribution-analysisagentscope-ai/QwenPaw-Data	Skill	196	7d ago	Apache-2.0	A	54	Claude Code, Codex
bi-retention-analysisagentscope-ai/QwenPaw-Data	Skill	196	7d ago	Apache-2.0	A	142	Claude Code, Codex
bi-adaptive-thresholdagentscope-ai/QwenPaw-Data	Skill	196	7d ago	Apache-2.0	A	72	Claude Code, Codex
bi-dashboard-generationagentscope-ai/QwenPaw-Data	Skill	196	7d ago	Apache-2.0	A	94	Claude Code, Codex