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/instructionsgit 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 | $0.00027 | $0.00862 |
| Opus 5 | $0.00014 | $0.00431 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade B, and why
instructions 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 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
### Show Instructions for a Filtered Server Set How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions Command
Show CLI-mode instructions for AI agents using a running 1MCP serve instance.
Synopsis
npx -y @1mcp/agent instructions [options]
Description
The instructions command is the entrypoint for CLI-mode agent workflows. It prints:
- A fixed playbook telling the agent to use
inspectbeforerun - A server summary section
- A server details section
- Per-server instruction blocks when the server provides them
Use this command first when an agent or terminal session needs current guidance from the running 1MCP instance.
In practice, instructions is what replaces a large direct-MCP starting surface in the agent loop. Instead of expecting the agent to carry every available tool and schema up front, 1MCP gives it a compact playbook plus the current inventory, then tells it to narrow further with inspect.
Output Structure
The output is designed to be agent-readable and includes:
=== PLAYBOOK ===- The required CLI workflow=== SERVER SUMMARY ===- One compact record per server=== SERVER DETAILS ===- Detailed records including instructions or availability notes
Each server entry includes metadata such as:
- Server name
- Server type
- Connection status
- Availability
- Tool count
- Whether instructions are available
Options
--url, -u <url>- Override auto-detected 1MCP server URL--context <name>- Use a named Runtime Target Context and its saved bearer token, if any--preset, -p <name>- Use a preset when querying the running server--tag-filter, -f <expression>- Apply an advanced tag filter expression--tags <tag>- Apply simple comma-separated tags
Examples
Show the Full CLI Playbook
npx -y @1mcp/agent instructions
Show Instructions for a Filtered Server Set
npx -y @1mcp/agent instructions --tags backend
Use a Saved Preset
npx -y @1mcp/agent instructions --preset development
Use a Runtime Target Context
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 · 113 lines · 27 tokens per session scan B fb3b1c5ca50c
instructions is a command published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 862 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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.
web-component
Create a new web component following the established project conventions.
send
Send a WhatsApp message using the wu MCP server.
count
Count WhatsApp messages in a chat.