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.
npx agentmods add agents/isaacsight/kernel/admingit clone --depth 1 https://github.com/isaacsight/kernelWhat 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.
| Model | Per session | Once 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 |
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.
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
Inboxfolder)
2. Client Scoring & Invoicing
- View client scores (triggered by
kernel.hatcommand) - 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
- Read memory — Call
agent_memory_readforadminto load prior context - Assess request — Determine which admin operation is needed
- Execute — Use the appropriate tools and Supabase queries
- Report — Provide clear summary of actions taken
- Write memory — Call
agent_memory_writewith 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 |
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.
- yesterday First seen · 125 lines · 0 tokens per session scan A 4364d47dbf3c
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.
Other agents, from other repositories
implementer
You are the implementer agent in the Polis automated pipeline.
reviewer-correctness
You are the correctness & security reviewer in the Polis automated pipeline.
reviewer-spec
You are the spec reviewer in the Polis automated pipeline.
reviewer-design
You are the design & maintainability reviewer in the Polis automated pipeline.
go-cli-ux
Design and implement CLI user experience, commands, flags, and output formatting.
architect
Design and plan application architecture using MCP tools.