Borrowing it
Nothing to install: this file belongs to damionrashford/Adversaria. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/damionrashford/Adversaria/main/CLAUDE.mdgit clone --depth 1 https://github.com/damionrashford/AdversariaWrote 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/instructions/damionrashford/adversaria/claude-md)<a href="https://agentmods.dev/instructions/damionrashford/adversaria/claude-md"><img src="https://agentmods.dev/badge/instructions/damionrashford/adversaria/claude-md/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/instructions/damionrashford/adversaria/claude-md"><img src="https://agentmods.dev/badge/instructions/damionrashford/adversaria/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03137 | $0.03137 |
| Opus 5.5 | $0.01255 | $0.01255 |
| Sonnet 5.5 | $0.00627 | $0.00627 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
Adversaria CLAUDE.md 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repository is
Adversaria is a Claude Code plugin, not an application. There is no build step, no bundler, and no dependency manifest. Every file is one of three things: a JSON manifest, a Markdown instruction file that Claude reads at runtime, or a TypeScript file run directly by Bun.
The consequence: the Markdown is the product. Editing agents/*.md or skills/*/SKILL.md changes behavior as directly as editing code. Treat prose changes in those files with the same care as a code change, and re-read the frontmatter contract below before touching it.
The plugin is distributed through a public marketplace and runs on other people's machines, inside their projects. Nothing in this repo may hard-code an absolute path, assume a particular operating system or directory layout, or carry information specific to one contributor. Paths resolve through ${CLAUDE_PLUGIN_ROOT} and ${CLAUDE_SKILL_DIR} (see Path contract).
Development tooling
.claude/settings.json enables plugin-dev, Anthropic's official plugin-authoring toolkit, for anyone working in this repo. It is the authority on plugin structure — prefer it over recalling conventions from memory, since the plugin spec changes.
It loads automatically once the official marketplace is known locally. If Claude Code reports the marketplace is missing:
/plugin marketplace add anthropics/claude-plugins-official
| Component | Use it when |
|---|---|
plugin-dev:plugin-validator (agent) |
Before any commit that touches .claude-plugin/, hooks/hooks.json, or agent/skill frontmatter. Validates manifests and file layout. |
plugin-dev:skill-reviewer (agent) |
After editing any SKILL.md, especially the description — that field is what makes the skill auto-trigger. |
plugin-dev:agent-creator (agent) |
Adding a fourth agent, or reworking an existing agent's frontmatter. |
/plugin-dev:create-plugin (command) |
Scaffolding only. This plugin already exists; rarely needed here. |
plugin-dev:plugin-structure (skill) |
Questions about directory layout and manifest fields. |
plugin-dev:skill-development (skill) |
Writing or restructuring a skill, including references/ and progressive disclosure. |
plugin-dev:agent-development (skill) |
Agent frontmatter fields: model, tools, skills, memory, effort, maxTurns. |
plugin-dev:hook-development (skill) |
Anything in hooks/ — event names, matchers, exit-code contract, ${CLAUDE_PLUGIN_ROOT}. |
plugin-dev:command-development (skill) |
Slash-command surface and argument-hint. |
plugin-dev:mcp-integration (skill) |
Only if an MCP server is ever added. There is none today. |
plugin-dev:plugin-settings (skill) |
settings.json keys and plugin enablement scopes. |
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.
- 2mo ago First seen · 168 lines · 3,137 tokens per session scan A 495feb0cfd7f
Adversaria CLAUDE.md is an instructions file published in the GitHub repository damionrashford/Adversaria (11 stars, last pushed 2mo ago), licensed MIT. It adds 3,137 tokens to every session, about $0.0125 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 2026-09-03.
Adversaria CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Adversaria CLAUDE.mddamionrashford/Adversaria | Instructions file | 11 | 2mo ago | MIT | A | 3,137 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |