Adversaria: Instructions file for Claude Code

CLAUDE.md

Adversaria CLAUDE.md is an instructions file for Claude Code from damionrashford/Adversaria. It costs 3,137 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Claude Code, Anthropic’s coding assistant, when working on the Adversaria plugin. They describe the repository’s purpose, tools, commands, architecture, file rules, and path requirements.

In plain words
What is it for?
Guide development and editing of Adversaria agents, skills, manifests, and Bun-run TypeScript files.
Why use it?
They give the coding assistant the context needed to make compatible changes and avoid assumptions about the operating system, file locations, or build process.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is damionrashford/Adversaria's own configuration. It tells Claude Code how to work on Adversaria itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Adversaria configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/damionrashford/Adversaria/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/damionrashford/Adversaria

Made for: Claude Code.

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 Adversaria CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/damionrashford/adversaria/claude-md/github.svg)](https://agentmods.dev/instructions/damionrashford/adversaria/claude-md)
Your own site
<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.

agentmods 80×15 button for Adversaria CLAUDE.md

Your own site · 80×15
<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>
Per session 3,137 This file is loaded in full into every session.
When invoked 3,137 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.03137 $0.03137
Opus 5 $0.01569 $0.01569
Sonnet 5 $0.00627 $0.00627
Haiku 4.5 $0.00314 $0.00314

Measured 6d ago against content hash 495feb0cfd7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 6d 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.

CLAUDE.md · 168 lines

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.

Read the full file on GitHub · 168 lines

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. 6d ago First seen · 168 lines · 3,137 tokens per session scan A 495feb0cfd7f

Subscribe to this mod's changes

Adversaria CLAUDE.md is an instructions file published in the GitHub repository damionrashford/Adversaria (7 stars, last pushed 7d ago), licensed MIT. It adds 3,137 tokens to every session, about $0.0157 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 2026-09-03.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens