ev-adversarial-audit

ev-adversarial-audit is a skill for Claude Code, Codex from gaia-research/gaia-skill-tree. It costs 150 tokens per session (580 once invoked), scanned A, original, no licence file.

A quality-control step for checking collected evidence before it enters a data store. It looks for broken links, incorrect repository URLs, subjective descriptions, outdated notes, and other catalogue problems.

In plain words
What is it for?
It is for auditing an evidence data lake, including links, URL formats, wording, migration notes, and benchmark catalogue entries.
Why use it?
It catches unreliable or hard-to-use evidence before later steps depend on it. This helps prevent bad data from being ingested.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

Good fit It is for auditing an evidence data lake, including links, URL formats, wording, migration notes, and benchmark catalogue entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gaia-research/gaia-skill-tree/ev-adversarial-audit
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 ev-adversarial-audit
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.

agentmods badge for ev-adversarial-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/gaia-research/gaia-skill-tree/ev-adversarial-audit/github.svg)](https://agentmods.dev/skills/gaia-research/gaia-skill-tree/ev-adversarial-audit)
Your own site
<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-tree/ev-adversarial-audit"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-tree/ev-adversarial-audit/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 ev-adversarial-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-tree/ev-adversarial-audit"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-tree/ev-adversarial-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 580 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.00580
Opus 5 $0.00075 $0.00290
Sonnet 5 $0.00030 $0.00116
Haiku 4.5 $0.00015 $0.00058

Measured 12d ago against content hash fc8dfc414c89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ev-adversarial-audit 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 12d 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/ev-adversarial-audit/SKILL.md · 35 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.

  1. 12d ago First seen · 35 lines · 150 tokens per session scan A fc8dfc414c89

Subscribe to this mod's changes

ev-adversarial-audit is a skill published in the GitHub repository gaia-research/gaia-skill-tree (19 stars, last pushed today), with no licence file. It adds 150 tokens to every session and 580 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

dbrain-processor

Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

smixs/agent-second-brain · 60 tokens

bi-clustering

A business-analysis skill that places similar business objects—such as users, products, or shops—into groups. It can use a two-by-two matrix based on two measures or clustering based on several features.

agentscope-ai/QwenPaw-Data · 107 tokens

data-science-analysis

Computes a numeric or categorical answer to a quantitative data-science question by cleaning and analyzing local data files (CSV, Excel, TSV, and scientific formats .npz/.fits/.h5) with pandas, numpy, and scipy. Use whenever a task ships its own dataset (in whatever local directory it provides) and asks you to derive…

agentscope-ai/QwenPaw-Data · 237 tokens

bi-retention-analysis

A workflow for measuring user retention, meaning how many users return or repeat a chosen activity after an initial event such as registration or first use.

agentscope-ai/QwenPaw-Data · 142 tokens

bi-attribution-analysis

A business-analysis skill that measures how much each group or dimension value contributed to a metric's change. It supports totals that can be added directly, rates such as conversion rate, and weighted averages such as average order value.

agentscope-ai/QwenPaw-Data · 54 tokens

bi-adaptive-threshold

A tool for calculating a change threshold from the natural variation in historical time-series data. A threshold is the boundary above which a change is treated as notable.

agentscope-ai/QwenPaw-Data · 72 tokens