config

A command for configuring the Claude RAG plugin, including its connection, captured data, retrieval behavior, and privacy settings.

In plain words
What is it for?
Use it to set an endpoint and API key, choose capture and RAG modes, redact secrets, exclude credentials or .env files, view settings, reset defaults, or test the connection.
Why use it?
It lets developers control what is recorded, how past context is retrieved, and which sensitive files or values are excluded.

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/thisisyoyodev/claude-rag/config
Clone the repo
git clone --depth 1 https://github.com/ThisisYoYoDev/claude-rag
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00020 $0.00296
Opus 5 $0.00010 $0.00148
Sonnet 5 $0.00004 $0.00059
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash ae0e036f8b03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

config scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{}'
commands/config.md · 40 lines

What it actually says

RAG Configuration

Configure: "$ARGUMENTS"

  1. Read current config:

    cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{}'
    
  2. If argument matches a section, go there. Otherwise main menu.

  • "Connection — endpoint & API key"
  • "Capture — what to record"
  • "RAG Mode — auto injection behavior"
  • "Privacy — secret redaction"
  • "Show current config"
  • "Reset to defaults"
  • "Test connection" (uses mcp__plugin_claude-rag_rag__health)

Connection

Local or Cloud? If Cloud: endpoint + API key.

Capture (multiSelect)

User prompts / AI outputs / Tool calls / Tool results / Sub-agents / Multimodal

RAG Mode

Off / Manual / Auto (recommended) / Aggressive

  • threshold and max tokens settings

Privacy (multiSelect)

Redact secrets / Exclude .env / Exclude credentials

Config path: ~/.claude/plugins/claude-rag/config.json

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 · 40 lines · 20 tokens per session scan B ae0e036f8b03

Subscribe to this mod's changes

config is a command published in the GitHub repository ThisisYoYoDev/claude-rag (9 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 296 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.