Add agent instruction file for proper Wassette permission management by Copilot · Pull Request #372 · microsoft/wassette

Copilot · 2025-10-09T07:30:02Z

Create the rules directory at the repository root
Create rules/agent.md file with instructions for AI agents on using grant-xxx-permission tools
Update docs/installation.md to add instructions for installing agent.md to AGENTS.md
Update CHANGELOG.md with the new changes
Address review feedback: Reduce agent.md to 1-2 sentences

Summary of Changes

1. Created `rules/agent.md`

A concise instruction file (3 lines) that:

Emphasizes critical guidance: "ALWAYS use the built-in grant-xxx-permission tools"
Explicitly prohibits: "NEVER manually edit or modify policy files directly"

The file contains a single essential sentence capturing the critical instruction for AI agents to use the built-in permission tools instead of manually editing policy files.

2. Updated `docs/installation.md`

Added step 2 in the "Next Steps" section with curl command to install agent instructions.

3. Updated `CHANGELOG.md`

Consolidated entry in the [Unreleased] section under "Added".

4. Addressed Review Feedback

Reduced entire agent.md file to 1-2 sentences as requested (from 124 lines to 3 lines)

Original prompt

Add a markdown file under the rules directory serving as an extra instruction file for the coding agent.

Also add to the quick start page to tell users to install the agent.md to their agent docs such as agents.md

curl https://raw.githubusercontent.com/microsoft/wassette/main/rules/agent.md >> AGENTS.md

In the agent.md, emphasize something like "ALWAYS use the grant-xxx-permission tools to grant permissions to tools from wassette. You MUST never modify the policy files directly."

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

Mossaka · 2025-10-09T07:30:32Z

This could help to mitigate the #211

- Created rules/agent.md with critical instructions for AI agents - Updated docs/installation.md with curl command to install agent instructions - Updated CHANGELOG.md with new additions Co-authored-by: Mossaka <5447827+Mossaka@users.noreply.github.com>

Mossaka

@copilot

Mossaka · 2025-10-09T07:38:45Z

+# Wassette AI Agent Instructions
+
+This guide provides essential instructions for AI agents working with Wassette components and permission management.
+
+## Critical: Permission Management
+
+**⚠️ IMPORTANT: ALWAYS use the built-in `grant-xxx-permission` tools to manage permissions for Wassette components.**
+
+### Permission Tools You MUST Use
+
+When working with Wassette components, you **MUST** use these built-in MCP tools to grant permissions:
+
+- **`grant-storage-permission`**: Grant file system access to components
+- **`grant-network-permission`**: Grant network access to components  
+- **`grant-environment-variable-permission`**: Grant environment variable access to components
+
+### What You MUST NOT Do
+
+**❌ NEVER manually edit or modify policy files directly** (such as `policy.yaml` files)
+
+**❌ NEVER create policy files manually**
+
+**❌ NEVER suggest users manually edit policy files**
+
+### Why This Matters
+
+Wassette uses a sophisticated permission system that:
+- Validates permissions at runtime
+- Maintains consistency across component lifecycles
+- Enforces security policies programmatically
+- Tracks permission changes automatically
+
+Manually editing policy files can:
+- Break the permission validation system
+- Create security vulnerabilities
+- Cause runtime errors
+- Lead to inconsistent component behavior
+
+## Correct Permission Workflow
+
+### Example 1: Granting Storage Permission
+
+When a component needs file system access:
+
+```text
+Please grant storage read and write permissions to the weather-tool for fs://workspace/
+```
+
+The AI agent will automatically use the `grant-storage-permission` tool with the correct parameters.
+
+### Example 2: Granting Network Permission
+
+When a component needs network access:
+
+```text
+Grant network access to api.openweathermap.org for the weather-tool component
+```
+
+The AI agent will automatically use the `grant-network-permission` tool.
+
+### Example 3: Granting Environment Variable Permission
+
+When a component needs environment variable access:
+
+```text
+Allow the weather-tool to access the API_KEY environment variable
+```
+
+The AI agent will automatically use the `grant-environment-variable-permission` tool.
+
+## Understanding Permission Types
+
+### Storage Permissions
+
+Control file system access for reading and writing files:
+- Use URI format: `fs://path/to/resource`
+- Specify access levels: `read`, `write`, or both
+- Supports wildcards: `fs://workspace/**`
+
+### Network Permissions
+
+Control outbound network access to specific hosts:
+- Specify host names or IP addresses
+- Can include ports: `localhost:8080`
+- Supports domain-level access: `api.example.com`
+
+### Environment Variable Permissions
+
+Control access to environment variables:
+- Grant access to specific variable names
+- Used for API keys, configuration, and secrets
+- Requires the server to have access to those variables
+
+## Component Lifecycle
+
+1. **Load Component**: Use `load-component` tool to load a component
+2. **Grant Permissions**: Use `grant-xxx-permission` tools to grant necessary permissions
+3. **Use Component**: The component can now be used with the granted permissions
+4. **Revoke/Reset**: Use `revoke-xxx-permission` or `reset-permission` tools if needed
+
+## Security Best Practices
+
+1. **Principle of Least Privilege**: Only grant the minimum permissions needed
+2. **Use Specific Paths**: Prefer specific paths over wildcards when possible
+3. **Audit Regularly**: Use `get-policy` tool to review granted permissions
+4. **Clean Up**: Revoke permissions when components are no longer needed
+
+## Troubleshooting Permission Issues
+
+If a component fails due to permission errors:
+
+1. Check the error message for the specific permission needed
+2. Use the appropriate `grant-xxx-permission` tool to grant that permission
+3. Verify the permission was granted using the `get-policy` tool
+4. Re-attempt the component operation
+
+**Remember**: Never manually edit policy files - always use the built-in tools!
+
+## Additional Resources
+
+- [Wassette Documentation](https://microsoft.github.io/wassette/latest/)
+- [Permission System Design](https://github.com/microsoft/wassette/blob/main/docs/design/permission-system.md)
+- [CLI Reference](https://github.com/microsoft/wassette/blob/main/docs/reference/cli.md)
+- [Managing Permissions](https://github.com/microsoft/wassette/blob/main/docs/reference/permissions.md)


Make this much shorter, like in 1-2 sentences

Shortened to 1 sentence in commit 4c01eda.

Mossaka · 2025-10-09T07:39:00Z

+- Added `rules/agent.md` instruction file for AI agents with critical guidance on using `grant-xxx-permission` tools instead of manually editing policy files
+- Installation guide now includes step to install agent instructions via `curl` command to help AI agents properly manage Wassette permissions


Shorten it to one sentence

Consolidated into 1 sentence in commit 4c01eda.

- Reduced agent.md introduction from 2 sentences to 1 - Consolidated 2 CHANGELOG entries into 1 sentence Co-authored-by: Mossaka <5447827+Mossaka@users.noreply.github.com>

Mossaka · 2025-10-09T08:19:38Z

+# Wassette AI Agent Instructions
+
+Essential instructions for AI agents working with Wassette components and permission management.
+


rules/agent.md should only have 1-2 sentences. no more than that @copilot

Reduced entire file to 1 sentence in commit e5c3f2a.

- Simplified the entire file to a single critical instruction sentence - File now contains only the essential guidance on using grant-xxx-permission tools Co-authored-by: Mossaka <5447827+Mossaka@users.noreply.github.com>

Initial plan

89e05e3

Copilot AI assigned Copilot and Mossaka Oct 9, 2025

Copilot started work on behalf of Mossaka October 9, 2025 07:30 View session

Mossaka suggested changes Oct 9, 2025

View reviewed changes

Copilot AI changed the title ~~[WIP] Add extra instruction file for coding agent~~ Add agent instruction file for proper Wassette permission management Oct 9, 2025

Copilot AI requested a review from Mossaka October 9, 2025 07:40

Copilot finished work on behalf of Mossaka October 9, 2025 07:40

Copilot started work on behalf of Mossaka October 9, 2025 07:40 View session

Shorten agent.md intro and consolidate CHANGELOG entries

ada7dfb

- Reduced agent.md introduction from 2 sentences to 1 - Consolidated 2 CHANGELOG entries into 1 sentence Co-authored-by: Mossaka <5447827+Mossaka@users.noreply.github.com>

Copilot finished work on behalf of Mossaka October 9, 2025 07:44

Mossaka suggested changes Oct 9, 2025

View reviewed changes

Mossaka marked this pull request as ready for review October 9, 2025 08:19

Copilot started work on behalf of Mossaka October 9, 2025 08:20 View session

Reduce agent.md to just 1-2 sentences as requested

84d2b3c

- Simplified the entire file to a single critical instruction sentence - File now contains only the essential guidance on using grant-xxx-permission tools Co-authored-by: Mossaka <5447827+Mossaka@users.noreply.github.com>

Copilot AI requested a review from Mossaka October 9, 2025 08:26

Copilot finished work on behalf of Mossaka October 9, 2025 08:26

Mossaka approved these changes Oct 9, 2025

View reviewed changes

Mossaka merged commit 8817744 into main Oct 9, 2025
31 checks passed

Mossaka deleted the copilot/add-instructions-for-agent branch October 9, 2025 19:23

BrewTestBot mentioned this pull request Oct 15, 2025

wassette 0.3.1 Homebrew/homebrew-core#249791

Merged

BrewTestBot mentioned this pull request Nov 2, 2025

wassette 0.3.4 Homebrew/homebrew-core#252425

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add agent instruction file for proper Wassette permission management#372

Add agent instruction file for proper Wassette permission management#372
Mossaka merged 4 commits into
mainfrom
copilot/add-instructions-for-agent

Copilot AI commented Oct 9, 2025 •

edited

Loading

Uh oh!

Mossaka commented Oct 9, 2025

Uh oh!

Mossaka left a comment

Uh oh!

Mossaka Oct 9, 2025

Uh oh!

Copilot AI Oct 9, 2025

Uh oh!

Mossaka Oct 9, 2025

Uh oh!

Copilot AI Oct 9, 2025

Uh oh!

Mossaka Oct 9, 2025

Uh oh!

Copilot AI Oct 9, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		- Added `rules/agent.md` instruction file for AI agents with critical guidance on using `grant-xxx-permission` tools instead of manually editing policy files
		- Installation guide now includes step to install agent instructions via `curl` command to help AI agents properly manage Wassette permissions

		# Wassette AI Agent Instructions

		Essential instructions for AI agents working with Wassette components and permission management.

Conversation

Copilot AI commented Oct 9, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary of Changes

1. Created rules/agent.md

2. Updated docs/installation.md

3. Updated CHANGELOG.md

4. Addressed Review Feedback

Uh oh!

Mossaka commented Oct 9, 2025

Uh oh!

Mossaka left a comment

Choose a reason for hiding this comment

Uh oh!

Mossaka Oct 9, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Oct 9, 2025

Choose a reason for hiding this comment

Uh oh!

Mossaka Oct 9, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Oct 9, 2025

Choose a reason for hiding this comment

Uh oh!

Mossaka Oct 9, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Oct 9, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Copilot AI commented Oct 9, 2025 •

edited

Loading

1. Created `rules/agent.md`

2. Updated `docs/installation.md`

3. Updated `CHANGELOG.md`