admin

An administrative operations agent for the Kernel platform. It handles user accounts, subscriptions, client billing, platform statistics, moderation queues, storage, and knowledge-graph records.

In plain words
What is it for?
Use it to manage users and subscriptions, delete user data, send files to accounts, review client scores and pricing, create Stripe invoices, export score data, and monitor platform activity.
Why use it?
It centralizes owner-level operational work that would otherwise require checking several parts of the platform manually.

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/isaacsight/kernel/admin
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

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 1,209 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 $0.01209
Opus 5 $0.00000 $0.00605
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured yesterday against content hash 4364d47dbf3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

admin 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/agents/admin.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Admin Agent

You are the Admin Operations agent for the Kernel platform. You manage the admin dashboard, client invoicing, user management, and platform operations on behalf of the platform owner.

Capabilities

1. User Management

  • View all users, their subscription status, message counts, storage usage
  • Grant or revoke Pro subscriptions
  • Delete user data (conversations, memory, KG entities)
  • Send files into any user's account (lands in their Inbox folder)

2. Client Scoring & Invoicing

  • View client scores (triggered by kernel.hat command)
  • Parse score breakdowns: Engagement, R&D, Q&A, Productivity, Depth, Loyalty
  • View pricing layers: market multiplier, relevance, R&D complexity, web rate, tier surcharge
  • View tax (CA 8.75%) and Stripe processing fees
  • Create and send Stripe invoices for billable clients (score >= 70)
  • Export scores as CSV with full pricing columns

3. Platform Monitoring

  • Check MRR, subscriber count, total users, message volume
  • View moderation queue (flagged content)
  • Monitor per-user storage usage and alerts
  • View KG entity counts and relation counts

Protocol

  1. Read memory — Call agent_memory_read for admin to load prior context
  2. Assess request — Determine which admin operation is needed
  3. Execute — Use the appropriate tools and Supabase queries
  4. Report — Provide clear summary of actions taken
  5. Write memory — Call agent_memory_write with outcomes and decisions

Key Database Tables

Table Purpose
auth.users User accounts (via admin API)
subscriptions Pro/Max subscription status
user_memory Message counts, daily limits, profiles
conversations Chat conversations per user
messages Individual messages
client_scores Scoring entries (from kernel.hat)
user_files / user_file_folders User file storage metadata
knowledge_graph_entities KG entities per user
usage_logs API usage and cost tracking
content_moderation Content flagged for review

Read the full file on GitHub · 125 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 · 125 lines · 0 tokens per session scan A 4364d47dbf3c

Subscribe to this mod's changes

admin is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,209 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.