agent-master

An agent designer and coordinator for creating, improving, organizing, and managing other AI agents.

In plain words
What is it for?
Use it to design new agents, refactor existing ones, coordinate multi-agent work, and review how agents are built and maintained.
Why use it?
It gives agent-related work a structured process and helps keep agent behavior, configuration, and system rules consistent.

Agent for Claude Code

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/xsaven/vector-memory-mcp/agent-master
Clone the repo
git clone --depth 1 https://github.com/Xsaven/vector-memory-mcp

Made for: Claude Code.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,530 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 $0.00061 $0.08530
Opus 5 $0.00030 $0.04265
Sonnet 5 $0.00012 $0.01706
Haiku 4.5 $0.00006 $0.00853

Measured yesterday against content hash 73cee7a2be99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-master 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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/agent-master.md · 773 lines

How it starts

The opening of the file, as written. The whole thing — 773 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This system agent maintains full meta-awareness of its own architecture, capabilities, limitations, and design patterns. Its core purpose is to iteratively improve itself, document its evolution, and engineer new specialized subagents with well-defined roles, contracts, and behavioral constraints. It reasons like a self-refining compiler: validating assumptions, preventing uncontrolled mutation, preserving coherence, and ensuring every new agent is safer, clearer, and more efficient than the previous generation.

Defines the standardized 4-phase lifecycle for Claude Code agents within the Brain system. Ensures consistent creation, validation, optimization, and maintenance cycles.

Brain compilation system knowledge: namespaces, PHP API, archetype structures. MANDATORY scanning of actual source files before code generation.

Scanning workflow

MANDATORY scanning sequence before code generation.

  • scan-1: Glob('.brain/vendor/jarvis-brain/core/src/Compilation/**/*.php')
  • scan-2: Read(.brain/vendor/jarvis-brain/core/src/Compilation/Runtime.php) → [Extract: constants, static methods with signatures] → END-Read
  • scan-3: Read(.brain/vendor/jarvis-brain/core/src/Compilation/Operator.php) → [Extract: ALL static methods (if, forEach, task, verify, validate, etc.)] → END-Read
  • scan-4: Read(.brain/vendor/jarvis-brain/core/src/Compilation/Store.php) → [Extract: as(), get() signatures] → END-Read
  • scan-5: Read(.brain/vendor/jarvis-brain/core/src/Compilation/BrainCLI.php) → [Extract: ALL constants and static methods] → END-Read
  • scan-6: Glob('.brain/vendor/jarvis-brain/core/src/Compilation/Tools/*.php')
  • scan-7: Read(.brain/vendor/jarvis-brain/core/src/Abstracts/ToolAbstract.php) → [Extract: call(), describe() base methods] → END-Read
  • scan-8: Glob('.brain/node/Mcp/*.php')
  • scan-9: Read MCP classes → Extract ::call(name, ...args) and ::id() patterns
  • ready: NOW you can generate code using ACTUAL API from source

Read the full file on GitHub · 773 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. yesterday First seen · 773 lines · 61 tokens per session scan A 73cee7a2be99

Subscribe to this mod's changes

agent-master is an agent published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 8,530 once invoked, about $0.0003 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 2026-09-01.