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 commands/1mcp-app/agent/admingit clone --depth 1 https://github.com/1mcp-app/agentWhat 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 | $0.00010 | $0.00410 |
| Opus 5 | $0.00005 | $0.00205 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
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.
What it actually says
Admin Commands
admin manages Admin accounts and CLI Admin sessions for named Runtime Target Contexts. Credential commands require --context; --url is not supported for Admin credentials.
1mcp admin <subcommand> [options]
bootstrap
1mcp admin bootstrap --username <name> --password <password> [--json]
Create the first Admin Account for the selected local Runtime Scope. Both --username and --password are required. --json defaults to false.
login
1mcp admin login --context <name> [--username <name>] [--password <password>] [--json]
Create a CLI Admin session for a named context. --json defaults to false.
On an interactive terminal, omitted credentials can be prompted. With --json or a non-interactive stdin, both --username and --password are required.
status
1mcp admin status --context <name> [--json]
Show the saved Admin session status. --json defaults to false.
logout
1mcp admin logout --context <name> [--forget] [--json]
1mcp admin logout --context local --all-local [--json]
Revoke a CLI Admin session. --forget clears only the local session reference without confirming remote revocation. --all-local clears every local Admin session reference and requires --context local. All three flags default to false.
Example
1mcp target add prod https://mcp.example.com/mcp --use
1mcp admin login --context prod --username operator
1mcp admin status --context prod
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 · 58 lines · 10 tokens per session scan A f1664a43cb67
admin is a command published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 3d ago), licensed Apache-2.0. It adds 10 tokens to every session and 410 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 2026-08-30.
Other commands, from other repositories
go
MCP tool management and workflow proxy.
strict-development-rules
These rules apply strictly to all code modifications and additions within the Gemini CLI project.
release-harn
Run the tag-first Harn release workflow.
harn-release
Run the tag-first Harn release workflow.
web-component
Create a new web component following the established project conventions.
send
Send a WhatsApp message using the wu MCP server.