planning-and-task-breakdown

An agent skill by addyosmani, from addyosmani/agent-skills. Tags: developer-tools, documents.

What it does

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add addyosmani/agent-skills --skill planning-and-task-breakdown

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/addyosmani/agent-skills
cp -r agent-skills/skills/planning-and-task-breakdown ~/.claude/skills/planning-and-task-breakdown

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a read-only planning aid that writes task-planning artifacts like `tasks/plan.md` and `tasks/todo.md` in the project workspace. It does not run code, access secrets, or reach out over the network; the main effect is limited, deliberate filesystem writes for planning and tracking.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code evaluation are defined; it only instructs the agent to read and write markdown planning files.
Network access	0 (none)	The skill contains no download, upload, API, or remote-host communication steps.
Filesystem reach	1 (low)	It explicitly creates and updates local planning files such as `tasks/plan.md` and `tasks/todo.md`, but confines writes to the workspace.
Secrets & credentials	0 (none)	There is no instruction to read, request, or expose tokens, passwords, `.env` files, or other credentials.
Privilege & persistence	0 (none)	The skill does not request sudo, global installs, services, shell-profile edits, or other privilege changes.
Instruction hijack surface	0 (none)	The text emphasizes procedural safeguards like "Do NOT write code during planning" and "stop and ask" on conflicting plans; it does not tell the agent to ignore rules or hidden instructions.
Irreversible actions	0 (none)	It only creates a plan and task list; it does not itself deploy, publish, send messages, pay, book, or delete anything.
Transparency	0 (none)	The skill file is plain markdown with no binaries, encoded blobs, or runtime-generated code.

Before installing

Check whether `tasks/plan.md` or `tasks/todo.md` already exists with open checkboxes before using it.
Confirm your project uses the default local task list rather than an external tracker.
Review the repo's agent rules for any alternate planning location or workflow.
If you only need a small, obvious change, skip this skill and edit directly.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: addyosmani/agent-skills (all skills from this repository)
Path: skills/planning-and-task-breakdown/SKILL.md
Branch: main
Updated: 2026-09-19

code-review-and-quality — Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.
constraint-driven-development — Establishes a project's quality bar as a written contract and stops agents quietly lowering it.
context-engineering — Optimizes agent context setup.
deprecation-and-migration — Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another.
documentation-and-adrs — Records decisions and documentation.
doubt-driven-development — Subjects every non-trivial decision to a fresh-context adversarial review before it stands.