agent-bootstrap

A command that analyzes a codebase and generates project-specific expert agents for coding work.

In plain words
What is it for?
Use it to scan a project quickly, at different depths, focus on a specific area, preview results, generate only required agents, or create a broader expert suite.
Why use it?
It reduces the need to design every specialist manually and can update agents when the project changes.

Command

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 commands/closedloop-ai/claude-plugins/agent-bootstrap
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,910 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 $0.00000 $0.01910
Opus 5 $0.00000 $0.00955
Sonnet 5 $0.00000 $0.00382
Haiku 4.5 $0.00000 $0.00191

Measured 2d ago against content hash c28959b8bf43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 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.

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.

plugins/bootstrap/commands/agent-bootstrap.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Bootstrap Command

Analyzes a codebase and automatically generates a custom suite of project-specific domain expert agents tailored to the project.

Usage

/agent-bootstrap [options]

Options

Core Options

  • --target-command <name> - Target command to generate agents for (default: "code")
  • --depth quick|medium|deep - Discovery thoroughness level (default: "medium")
    • quick: Fast scan, basic detection
    • medium: Balanced analysis with pattern recognition
    • deep: Comprehensive codebase analysis
  • --focus <area> - Constrain analysis to specific areas (frontend, backend, infra, mobile, web)
  • --output-dir <path> - Where to write generated agents (default: .claude/agents/)

Execution Modes

  • --dry-run - Preview what would be generated without writing files
  • --interactive - Ask clarifying questions during discovery
  • --update - Regenerate outdated agents based on project changes
  • --minimal - Generate only required agents (test-strategist, security-privacy)
  • --enhance - Run full analysis and generate comprehensive agent suite
  • --add-domain <domain> - Add agents for specific domain (data-persistence, caching, etc.)

Conflict Resolution

  • --strategy backup|skip|overwrite|interactive - How to handle existing agent files
    • backup (default): Backup existing files to .claude/agents/backup-{timestamp}/ before overwriting
    • skip: Only generate new agents, skip existing ones
    • overwrite: Replace all agents unconditionally (with warning)
    • interactive: Prompt for decision on each conflicting agent

Description

The Agent Bootstrap system is a meta-orchestrator that:

  1. Analyzes your codebase by reading documentation (CLAUDE.md, README.md, architecture docs)
  2. Identifies domains of work (not frameworks) - API backend, data persistence, caching, frontend, mobile, etc.
  3. Maps domains to expert agents based on project complexity and technology choices
  4. Intelligently decomposes complex agents into specialists where valuable
  5. Generates agent prompts using LLM expertise (no templates - agents write agents!)

Read the full file on GitHub · 278 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 First seen · 278 lines · 0 tokens per session scan A c28959b8bf43

Subscribe to this mod's changes

agent-bootstrap is a command published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,910 tokens. 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 2026-08-30.