custom_instructions
Optional custom instructions to guide the agent beyond the issue body. Use this to provide additional context, constraints, or guidance that is not captured in the issue description (string, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/custom-instructions.md
What custom_instructions does on GitHub
AI agents call custom_instructions to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why custom_instructions is rated Low
This tool functions as a configuration or annotation mechanism that provides input/guidance to an agent. It retrieves or uses optional metadata to inform behavior, making it a Read operation. It has no side effects on repository state, issues, pull requests, or any other data.
From the tool's definition The tool 'custom_instructions' is described as 'Optional custom instructions to guide the agent beyond the issue body.' It is a string parameter used to provide additional context, constraints, or guidance.
Attacks that exploit this kind of access
The rule that runs custom_instructions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For custom_instructions, this is the rule to start with:
custom_instructions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every custom_instructions call is checked against it from then on.
Questions about custom_instructions
Optional custom instructions to guide the agent beyond the issue body. Use this to provide additional context, constraints, or guidance that is not captured in the issue description (string, optional). It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP server in PolicyLayer and add a rule for custom_instructions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches GitHub. Nothing to install.
custom_instructions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the custom_instructions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for custom_instructions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
custom_instructions is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue