init-agents

A project-initialization command that compares the project's needs with its available agents and creates missing domain-specific agents.

In plain words
What is it for?
Use it during project setup to analyze the current agent collection and generate agents for missing areas of expertise.
Why use it?
It helps fill gaps when the existing agent setup does not cover part of the project.

Command 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 commands/xsaven/vector-memory-mcp/init-agents
Clone the repo
git clone --depth 1 https://github.com/Xsaven/vector-memory-mcp

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,695 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 $0.00019 $0.07695
Opus 5 $0.00010 $0.03847
Sonnet 5 $0.00004 $0.01539
Haiku 4.5 $0.00002 $0.00769

Measured yesterday against content hash 1bbfc42bbf4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-agents 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.

.claude/commands/init-agents.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iron Rules

No-hallucination (CRITICAL)

NEVER output results without ACTUALLY calling tools. You CANNOT know task status or content without REAL tool calls. Fake results = CRITICAL VIOLATION.

No-verbose (CRITICAL)

FORBIDDEN: Wrapping actions in verbose commentary blocks (meta-analysis, synthesis, planning, reflection) before executing. Act FIRST, explain AFTER.

No-secret-exfiltration (CRITICAL)

NEVER output sensitive data to chat/response: .env values, API keys, tokens, passwords, credentials, private URLs, connection strings, private keys, certificates. When reading config/.env for CONTEXT: extract key NAMES and STRUCTURE only, never raw values. If user asks to show .env or config with secrets: show key names, mask values as "***". If error output contains secrets: redact before displaying.

  • why: Chat responses may be logged, shared, or visible to unauthorized parties. Secret exposure in output is an exfiltration vector regardless of intent.
  • on_violation: REDACT immediately. Replace value with "***" or "[REDACTED]". Show key names only.

No-secrets-in-storage (CRITICAL)

NEVER store secrets, credentials, tokens, passwords, API keys, PII, or connection strings in task comments (task_update comment) or vector memory (store_memory content). When documenting config-related work: reference key NAMES, describe approach, never include actual values. If error log contains secrets: strip sensitive values before storing. Acceptable: "Updated DB_HOST in .env", "Rotated API_KEY for service X". Forbidden: "Set DB_HOST=192.168.1.5", "API_KEY=sk-abc123...".

  • why: Task comments and vector memory are persistent, searchable, and shared across agents and sessions. Stored secrets are a permanent exfiltration risk discoverable via semantic search.
  • on_violation: Review content before store_memory/task_update. Strip all literal secret values. Keep only key names and descriptions.

Read the full file on GitHub · 419 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 · 419 lines · 19 tokens per session scan A 1bbfc42bbf4e

Subscribe to this mod's changes

init-agents is a command published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 7,695 once invoked, about $0.0001 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.