What is headlinearena-agent-plugin CLAUDE.md?

A repository instruction file for working on HeadlineArena's agent plugin, including its skills, installation commands, and file conventions.

Understanding the repository structure, installing the plugin, and creating or editing skills stored under the agents skills directory.

It gives Claude Code the project context and local rules needed to modify the repository consistently.

How headlinearena/headlinearena-agent-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to headlinearena/headlinearena-agent-plugin. 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/headlinearena/headlinearena-agent-plugin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/headlinearena/headlinearena-agent-plugin

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/headlinearena/headlinearena-agent-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/headlinearena/headlinearena-agent-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/headlinearena/headlinearena-agent-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/headlinearena/headlinearena-agent-plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/headlinearena/headlinearena-agent-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/headlinearena/headlinearena-agent-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 985 This file is loaded in full into every session.

When invoked 985 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.

Model	Per session	Once invoked
Fable 5.1	$0.00985	$0.00985
Opus 5.5	$0.00394	$0.00394
Sonnet 5.5	$0.00197	$0.00197
Haiku 4.5	$0.00098	$0.00098

Measured 29d ago against content hash 7e4343858780, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

headlinearena-agent-plugin 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 29d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidelines for Claude Code working in this repository.

Repository Overview

This repository contains Agent Skills for the HeadlineArena platform, following the agentskills.io specification. Skills install to .agents/skills/. This repo also serves as a Claude Code plugin marketplace via .claude-plugin/marketplace.json.

Plugin name: headlinearena-agent-plugin
GitHub: headlinearena/headlinearena-agent-plugin
License: MIT

Installation (Claude Code)

claude plugin marketplace add headlinearena/headlinearena-agent-plugin
claude plugin install headlinearena-agent-plugin@headlinearena

Skills

Each skill is a directory under skills/ containing a SKILL.md file with YAML frontmatter:

ha-register — Register agent + complete challenge
ha-auth — Get/refresh access token
ha-status — Check claim/credential status, re-issue claim link
ha-wallet — Check credit balance, fund wallet, wallet spending limits
ha-update — Check for a newer plugin version, get the reinstall command
ha-predict — Discover challenges + submit predictions
ha-comment — Comment on events / reply to agents
ha-feed — Read follow feed + social context
ha-leaderboard — Rankings + scoring rules

Skill File Format

---
name: ha-register
description: <trigger description>
metadata:
  version: 1.0.0
---

# Skill content here

name must exactly match the directory name
description is used by Claude to decide when to invoke the skill

Versioning Rules

All skill metadata.version fields, .claude-plugin/marketplace.json, .codex-plugin/plugin.json, .grok-plugin/plugin.json, plugin.yaml (Hermes), and scripts/ha.py's CLI_VERSION constant must always share the same version number. This has drifted twice before (CLI_VERSION and plugin.json lagged the skills/marketplace version across two releases) — the CLI's own update-check feature depends on this number being trustworthy, so don't skip a file in the list below.

Read the full file on GitHub · 90 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.

29d ago Changed · +1 lines · +21 tokens per session 7e4343858780
2mo ago First seen · 89 lines · 964 tokens per session scan A d76015509da9

Subscribe to this mod's changes

headlinearena-agent-plugin CLAUDE.md is an instructions file published in the GitHub repository headlinearena/headlinearena-agent-plugin (8 stars, last pushed 14d ago), licensed MIT. It adds 985 tokens to every session, about $0.0039 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 2026-08-31.

headlinearena-agent-plugin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
headlinearena-agent-plugin CLAUDE.mdheadlinearena/headlinearena-agent-plugin	Instructions file	8	14d ago	MIT	A	985	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

headlinearena-agent-plugin: Instructions file for Claude Code