Skip to content

docs(agent-development): improve visibility of tools vs allowed-tools disambiguation #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sjnims merged 1 commit into from
Dec 8, 2025
Merged

docs(agent-development): improve visibility of tools vs allowed-tools disambiguation #28

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions plugins/plugin-dev/skills/agent-development/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@ Agents are autonomous subprocesses that handle complex, multi-step tasks indepen
- System prompt defines agent behavior
- Model and color customization

> **⚠️ Field Name Difference:** Agents use `tools` to restrict tool access. Skills use `allowed-tools` for the same purpose. Don't confuse these when switching between component types.

## When to Use Agents vs Commands vs Skills

| Component | Best For | Triggering | Example Use Case |
Expand Down Expand Up @@ -199,6 +201,8 @@ tools: ["Read", "Write", "Grep", "Bash"]
- Testing: `["Read", "Bash", "Grep"]`
- Full access: Omit field or use `["*"]`

> **Important:** Agents use `tools` while Skills use `allowed-tools`. The field names differ between component types. For skill tool restrictions, see the `skill-development` skill.

## System Prompt Design

The markdown body becomes the agent's system prompt. Write in second person, addressing the agent directly.
Expand Down
Loading