builtin-tasks

Install

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.

Security

Grade A, and why

builtin-tasks 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.

plugins/builtin-tasks/.claude-plugin/plugin.json · 20 lines

What it actually says

{
	"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
	"name": "builtin-tasks",
	"description": "Task orchestration using Claude Code's built-in task tools with slash commands for importing plans and executing tasks individually, sequentially, or with a team",
	"version": "1.31.0",
	"license": "Apache-2.0",
	"author": {
		"name": "Craig Motlin"
	},
	"commands": [
		"./commands/import-plan.md",
		"./commands/do-one-task.md",
		"./commands/do-all-tasks.md",
		"./commands/do-all-with-team.md",
		"./commands/sweep-todos.md"
	],
	"agents": ["./agents/do-task.md"],
	"skills": ["./skills/team-lead", "./skills/team-member"]
}

Changes

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.

Related

Other plugins, from other repositories