bootstrap

bootstrap is an agent for coding agents from vergil-project/vergil-claude-plugin. It costs 36 tokens per session (522 once invoked), scanned A, original, MIT.

A session-start checker for a specific development setup called the vergil-tooling ecosystem. It reads the repository profile, checks the current Git branch, looks for shared standards, and verifies a safety hook before code changes.

In plain words
What is it for?
Use it at the start of every coding session to produce a repository and environment preflight report without changing files.
Why use it?
It catches missing project information, unsafe branch choices, unavailable standards, or missing safeguards before work begins.

Agent

Part of the vergil plugin — 15 skills, 2 agents, 2 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vergil-project/vergil-claude-plugin/bootstrap
Clone the repo
git clone --depth 1 https://github.com/vergil-project/vergil-claude-plugin

Or install vergil, the plugin that ships this one along with the rest of its 15 skills, 2 agents, 2 hooks.

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 bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/agents/vergil-project/vergil-claude-plugin/bootstrap.svg)](https://agentmods.dev/agents/vergil-project/vergil-claude-plugin/bootstrap)
Your own site
<a href="https://agentmods.dev/agents/vergil-project/vergil-claude-plugin/bootstrap"><img src="https://agentmods.dev/badge/agents/vergil-project/vergil-claude-plugin/bootstrap.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00522
Opus 5 $0.00018 $0.00261
Sonnet 5 $0.00007 $0.00104
Haiku 4.5 $0.00004 $0.00052

Measured 3d ago against content hash c314a32dc853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap 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 3d 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.

agents/bootstrap.md · 75 lines

What it actually says

Session Bootstrap Agent

You are the session bootstrap agent for the vergil-tooling ecosystem. Your job is to validate the development environment and emit a preflight status report. You run at the start of every work session before any code changes.

Run each check below in order. Collect results and emit a single status report at the end. Do NOT make any changes to the repository.

1. Repository Profile

Read vergil.toml in the current working directory.

If it exists, extract and report from the [project] table:

  • repository_type
  • branching_model
  • primary_language
  • canonical_local_validation_command

If it does not exist, report: WARNING: No repository profile found.

2. Branch State

Run git branch --show-current and report the current branch.

If the branch is main or develop, report: WARNING: On protected branch. Create a feature branch before making changes.

3. Standards and Conventions

Check if ../standards-and-conventions exists as a directory.

If found, report: Standards repo: resolved locally.

If not found, report: WARNING: Standards repo not found locally. Using web source as fallback.

4. Hook Guard

Check if vrg-hook-guard is available on PATH and report the result.

If not found, report: WARNING: vrg-hook-guard not found. The Claude Code PreToolUse hook guard requires vergil-tooling to be installed.

Status Report Format

Emit the final report as a structured summary using this format:

=== Session Bootstrap ===
Repository:    <repo name from directory>
Profile:       <repository_type> | <branching_model> | <primary_language>
Branch:        <current branch> [WARNING if protected]
Validation:    <canonical_local_validation_command or "not configured">
Standards:     <local or web fallback>
Git hooks:     <hooks path or "NOT CONFIGURED">
=========================

If any warnings were emitted, add a Warnings section listing them all after the status block.

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. 3d ago First seen · 75 lines · 36 tokens per session scan A c314a32dc853

Subscribe to this mod's changes

bootstrap is an agent published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 522 once invoked, about $0.0002 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 2026-08-31.