agent-config: Instructions file for Claude Code

CLAUDE.md

agent-config CLAUDE.md is an instructions file for Claude Code from wardawgmalvicious/agent-config. It costs 9,686 tokens per session, scanned C, original, MIT.

Repository instructions for a collection of coding-agent configuration files, including skills, subagents, hooks, rules, and server templates. They explain how the files are organized and triggered.

In plain words
What is it for?
Use them when editing agent rules, Claude-format files, skills, hooks, settings, marketplace entries, or MCP server templates.
Why use it?
They prevent contributors from putting configuration in the wrong format, location, or scope.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is wardawgmalvicious/agent-config's own configuration. It tells Claude Code how to work on agent-config 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 agent-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wardawgmalvicious/agent-config. 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/wardawgmalvicious/agent-config/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wardawgmalvicious/agent-config

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 agent-config CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wardawgmalvicious/agent-config/claude-md.svg)](https://agentmods.dev/instructions/wardawgmalvicious/agent-config/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wardawgmalvicious/agent-config/claude-md"><img src="https://agentmods.dev/badge/instructions/wardawgmalvicious/agent-config/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 9,686 This file is loaded in full into every session.
When invoked 9,686 The same file — it is already loaded in full.
Security scan C 2 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 $0.09686 $0.09686
Opus 5 $0.04843 $0.04843
Sonnet 5 $0.01937 $0.01937
Haiku 4.5 $0.00969 $0.00969

Measured 2d ago against content hash 18ce9f584446, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

agent-config CLAUDE.md scanned grade C with 2 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| `claude/settings.json` | `~/.claude/settings.json` | plain copy, key-level merge | after `scripts/link-claude.ps1 -Force` |

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

`ls ~/.claude/skills | grep -E '^(fabric|pbir|pbid)-'` must come back
CLAUDE.md · 678 lines

How it starts

The opening of the file, as written. The whole thing — 678 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-config: repo instructions

This repo is the source for the user's coding-agent configuration (skills, a subagent, coding rules, hooks, MCP server templates, settings) — see README.md for the full picture. Claude Code is the harness it is written for and validated against; the content is structured so other tools can cherry-pick it, not promised to work in them.

Root CLAUDE.md is project-scope instruction and is never deployed. claude/CLAUDE.md is Claude's user-scope payload. They share a name and nothing else — neither is a mirror of the other. This file is also the repo's only project-scope instruction file. A .github/copilot-instructions.md and a root AGENTS.md each existed alongside it and each drifted; both were deleted rather than kept in sync. Don't add a third.

Layout convention: <tool>/ names the payload's format, not its only consumer. claude/ holds everything written in Claude Code's formats — subagent frontmatter, paths:-scoped rules, hook event wiring, user-scope CLAUDE.md and settings.json, and the MCP templates in Claude's mcpServers schema. skills/ is the only payload at the top level, because the Agent Skills format belongs to no single tool. Root CLAUDE.md is already taken by this file, so the user-scope one needs a directory — and once one payload file does, keeping the whole payload together is the consistent choice.

Config for this repo is a third category, and lives where each tool expects to find it rather than under a payload directory: .mcp.json, .claude/settings.json, and .vscode/mcp.json describe the servers and permissions used when editing this repo. Templates describe other repos; live config describes this one. The VS Code template is the one deliberate exception — it sits in .vscode/ next to the live file because that is exactly where it deploys.

.claude/settings.json holds more than servers and permissions: a skillOverrides block collapses all 41 platform skill descriptions to name-only in sessions here. That is deliberate, and it stays even though the workflow-only prune already keeps those skills out of ~/.claude/skills — it keeps them auditable from this repo and holds the shape ready for a future edit. Remember it when reasoning about triggers while working here: a description is the entire trigger mechanism, and in this repo the platform ones are not in the listing to be matched against.

Being a <tool>/ payload says nothing about how it deploys: everything under claude/ is copied, while skills/ is junctioned. Deployment mechanism is the table below; directory placement is only about format.

Read the full file on GitHub · 678 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. 2d ago Changed · +13 lines · +243 tokens per session 18ce9f584446
  2. 3d ago Changed · +445 lines · +6,380 tokens per session scan B → C 98d4b74ffc18
  3. 7d ago First seen · 220 lines · 3,063 tokens per session scan B ea35d0f82d02

Subscribe to this mod's changes

agent-config CLAUDE.md is an instructions file published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed 2d ago), licensed MIT. It adds 9,686 tokens to every session, about $0.0484 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens