What is vergil-claude-plugin CLAUDE.md?

A set of Claude Code instructions for the vergil-project/vergil-claude-plugin repository. It covers project guidance, approved memory changes, parallel work in Git worktrees, and available memory-related skills.

For guiding Claude Code sessions in the Vergil project, including memory setup, memory review, and parallel development.

It gives coding agents shared rules for working in the repository and prevents memory from being changed without human approval. It also explains how separate agents keep their work isolated.

How vergil-project/vergil-claude-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vergil-project/vergil-claude-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/vergil-project/vergil-claude-plugin/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vergil-project/vergil-claude-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/vergil-project/vergil-claude-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/vergil-project/vergil-claude-plugin/claude-md)

Your own site

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

Per session 3,702 This file is loaded in full into every session.

When invoked 3,702 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.03702	$0.03702
Opus 5	$0.01851	$0.01851
Sonnet 5	$0.00740	$0.00740
Haiku 4.5	$0.00370	$0.00370

Measured 8d ago against content hash 78386fd55828, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

vergil-claude-plugin CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

tools such as `gh`, `git commit`, or `curl`. Always write multi-line content

CLAUDE.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 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 when working in this repository.

Memory management

Memory is allowed with human approval. The authoritative policy is in the user's global ~/.claude/CLAUDE.md — agents must propose memory writes and suggest a destination (repo memory, global CLAUDE.md, or plugin/skill issue) before writing. See that file for the full workflow.

Available skills:

/vergil:memory-init — set up or update the policy header in a project's MEMORY.md.
/vergil:memory-audit — structured collaborative review of memory files.

Parallel AI agent development

This repository supports running multiple Claude Code agents in parallel via git worktrees. The convention keeps parallel agents' working trees isolated while preserving shared project memory (which Claude Code derives from the session's starting CWD).

Canonical spec: vergil-tooling/docs/specs/worktree-convention.md — full rationale, trust model, failure modes, and memory-path implications. The canonical text lives in vergil-tooling; this section is the local on-ramp.

Structure

<project-root>/                              ← sessions ALWAYS start here
  .git/
  CLAUDE.md, …                               ← main worktree (usually `develop`)
  .worktrees/                                ← container for parallel worktrees
    issue-<N>-<short-slug>/                  ← worktree on feature/<N>-<short-slug>
    …

Rules

Sessions always start at the project root. Never start Claude from inside .worktrees/<name>/. This keeps the memory-path slug stable and shared.
Each parallel agent is assigned exactly one worktree. The session prompt names the worktree (see Agent prompt contract below).
- For Read / Edit / Write tools: use the worktree's absolute path.
- For Bash commands that touch files: cd into the worktree first, or use absolute paths.
The main worktree is read-only. All edits flow through a worktree on a feature branch — the logical endpoint of the standing "no direct commits to develop" policy.
One worktree per issue. Don't stack in-flight issues. When a branch lands, remove the worktree before starting the next.
Naming: issue-<N>-<short-slug>. <N> is the GitHub issue number; <short-slug> is 2–4 kebab-case tokens.

Read the full file on GitHub · 355 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.

8d ago First seen · 355 lines · 3,702 tokens per session scan A 78386fd55828

Subscribe to this mod's changes

vergil-claude-plugin CLAUDE.md is an instructions file published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 6d ago), licensed MIT. It adds 3,702 tokens to every session, about $0.0185 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Memory and context

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

vergil-claude-plugin: Instructions file for Claude Code