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/xdg/xdg-claudeWrote 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/xdg/xdg-claude/adversarial-implementation)<a href="https://agentmods.dev/plugins/xdg/xdg-claude/adversarial-implementation"><img src="https://agentmods.dev/badge/plugins/xdg/xdg-claude/adversarial-implementation/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/xdg/xdg-claude/adversarial-implementation"><img src="https://agentmods.dev/badge/plugins/xdg/xdg-claude/adversarial-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
adversarial-implementation 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 19d 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.
What it actually says
{
"name": "adversarial-implementation",
"version": "0.3.0",
"description": "Implement TODO.md items one checkbox at a time via isolated subagents, with adversarial verification, code review, human-in-the-loop checks, and per-subsection commits",
"author": {
"name": "David Golden",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 96 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 19d ago Changed 3d31298427b3
- 1mo ago Changed 9c1782834d74
- 2mo ago First seen · 10 lines scan A 4a07f206ad59
adversarial-implementation is a plugin published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. 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 2026-08-30.
adversarial-implementation compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adversarial-implementationxdg/xdg-claude | Plugin | 20 | 6d ago | Apache-2.0 | A | — | Claude Code |
| pipecat-devpipecat-ai/pipecat | Plugin | 17k | yesterday | BSD-2-Clause | A | — | Claude Code |
| fix-allryanb/dotfiles | Plugin | 2.4k | 7d ago | MIT | A | — | Claude Code |
| han-githubtestdouble/han | Plugin | 337 | 5d ago | MIT | A | — | Claude Code |
| git-prCasper-Studios/casper-marketplace | Plugin | 15 | 7d ago | MPL-2.0 | A | — | Claude Code |
| gittechnicalpickles/pickled-claude-plugins | Plugin | 12 | yesterday | MIT | A | — | Claude Code |
| odin-gitOutlineDriven/odin-claude-plugin | Plugin | 40 | 1mo ago | Apache-2.0 | A | — | Claude Code |