Planning and task breakdown
Breaks a spec into small vertical-slice tasks with acceptance criteria, verification steps, sizes, dependency order and checkpoints, saved to tasks/todo.md or a named tracker. Use when a spec is ready but the work is too big to start in one go.
planning-and-task-breakdown- Author
- Addy Osmani
- Source
- addyosmani/agent-skills/skills/planning-and-task-breakdown @ 8c99fa3
- License
- MIT · Copyright (c) 2025 Addy Osmani
About this skill
What it does
The skill has the agent plan in read-only mode before any code: read the spec and the code it touches, then map dependencies and risks. It draws a dependency graph and cuts the work into vertical slices — "user can log in" across schema, API and UI — instead of layer by layer. Each task gets a description, testable acceptance criteria, verification commands, dependencies, likely files and a size from XS to XL. Anything L or larger is split again, as is a task with "and" in its title. Risky tasks go first, and every two or three tasks end in a checkpoint: tests, build and a review by you.
The result is tasks/plan.md (architecture decisions, risks, open questions) and a checklist in tasks/todo.md. If the project's agent rules or you name a tracker — GitHub Issues, Jira, Linear, beads — the tasks go there instead, one item each, with dependencies as tracker links. A plan that still has unchecked tasks for other work is never overwritten: the agent stops and asks.
The folder holds SKILL.md and the licence; the Definition of Done it mentions (../../references/definition-of-done.md) is in the author's repository and is not installed.
When to use it, and when not
Use it when you have a spec or clear requirements but the work is too big to start in one go, or will be split across agents or sessions.
Skip it for a single-file change with obvious scope, or when the spec already contains well-defined tasks.
How to run it
The install command below puts SKILL.md and the licence in place. The agent picks the skill up by its description when a spec needs breaking into tasks; to call it yourself:
- Claude Code:
/planning-and-task-breakdown, or ask for the skill by name. - Codex:
$planning-and-task-breakdown. - Cursor: type
/in the Agent chat and pickplanning-and-task-breakdown.
Example: /planning-and-task-breakdown Break SPEC.md into tasks. We track work in Linear, project BILL.
It usually comes after Spec-driven development, which defers to this skill for slicing and sizing. The tasks/todo.md format is what the author's /build command expects; that command is not part of this folder.
How it differs from similar skills
Writing implementation plans goes a level deeper: exact files, signatures, the test code for every step and a commit per task. This skill stays at task level: criteria, size and order. Spec to tickets also cuts vertical slices with blocking edges, asks you about granularity and publishes to the tracker set up by the author's setup-matt-pocock-skills or one you name; it runs only when called. Small steps builder carries out work in small commits rather than planning it. Spec-first kickoff writes a short plan along with the spec: four to ten steps, each with its own check, without sizes, dependencies or checkpoints. Wayfinder for huge work is for an effort too big and unclear to break down yet: its tickets are decisions, worked one per session until the way is clear.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/planning-and-task-breakdown/SKILL.md https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/SKILL.md -o ~/.claude/skills/planning-and-task-breakdown/LICENSE https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/LICENSE
curl -fsSL --create-dirs -o ~/.agents/skills/planning-and-task-breakdown/SKILL.md https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/SKILL.md -o ~/.agents/skills/planning-and-task-breakdown/LICENSE https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/LICENSE
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.claude\skills\planning-and-task-breakdown" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.agents\skills\planning-and-task-breakdown" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/addy-osmani/planning-and-task-breakdown/SKILL.md
SKILL.md
Planning and Task Breakdown
Overview
Decompose work into small, verifiable tasks with explicit acceptance criteria. Good task breakdown is the difference between an agent that completes work reliably and one that produces a tangled mess. Every task should be small enough to implement, test, and verify in a single focused session.
When to Use
- You have a spec and need to break it into implementable units
- A task feels too large or vague to start
- Work needs to be parallelized across multiple agents or sessions
- You need to communicate scope to a human
- The implementation order isn't obvious
When NOT to use: Single-file changes with obvious scope, or when the spec already contains well-defined tasks.
The Planning Process
Step 1: Enter Plan Mode
Before writing any code, operate in read-only mode:
- Read the spec and relevant codebase sections
- Identify existing patterns and conventions
- Map dependencies between components
- Note risks and unknowns
Do NOT write code during planning. The output is a plan document saved to tasks/plan.md and a task list recorded in the task list target (see Output Files; default tasks/todo.md), not implementation.
Step 2: Identify the Dependency Graph
Map what depends on what:
Database schema
│
├── API models/types
│ │
│ ├── API endpoints
│ │ │
│ │ └── Frontend API client
│ │ │
│ │ └── UI components
│ │
│ └── Validation logic
│
└── Seed data / migrations
Implementation order follows the dependency graph bottom-up: build foundations first.
Step 3: Slice Vertically
Instead of building all the database, then all the API, then all the UI — build one complete feature path at a time:
Bad (horizontal slicing):
Task 1: Build entire database schema
Task 2: Build all API endpoints
Task 3: Build all UI components
Task 4: Connect everything
Good (vertical slicing):
Task 1: User can create an account (schema + API + UI for registration)
Task 2: User can log in (auth schema + API + UI for login)
Task 3: User can create a task (task schema + API + UI for creation)
Task 4: User can view task list (query + API + UI for list view)
Each vertical slice delivers working, testable functionality.
Step 4: Write Tasks
Each task follows this structure, whether it lands in the markdown task list or as an item in an external tracker (see Output Files):
## Task [N]: [Short descriptive title]
**Description:** One paragraph explaining what this task accomplishes.
**Acceptance criteria:**
- [ ] [Specific, testable condition]
- [ ] [Specific, testable condition]
**Verification:**
- [ ] Tests pass: [the repository's focused-test command]
- [ ] Build succeeds: [the repository's build command]
- [ ] Manual check: [description of what to verify]
**Dependencies:** [Task numbers this depends on, or "None"]
**Files likely touched:**
- `src/path/to/file.ts`
- `tests/path/to/test.ts`
**Estimated scope:** [Small: 1-2 files | Medium: 3-5 files | Large: 5+ files]
Step 5: Order and Checkpoint
Arrange tasks so that:
- Dependencies are satisfied (build foundation first)
- Each task leaves the system in a working state
- Verification checkpoints occur after every 2-3 tasks
- High-risk tasks are early (fail fast)
Add explicit checkpoints to the task list target:
## Checkpoint: After Tasks 1-3
- [ ] All tests pass
- [ ] Application builds without errors
- [ ] Core user flow works end-to-end
- [ ] Review with human before proceeding
Task Sizing Guidelines
| Size | Files | Scope | Example |
|---|---|---|---|
| XS | 1 | Single function or config change | Add a validation rule |
| S | 1-2 | One component or endpoint | Add a new API endpoint |
| M | 3-5 | One feature slice | User registration flow |
| L | 5-8 | Multi-component feature | Search with filtering and pagination |
| XL | 8+ | Too large — break it down further | — |
If a task is L or larger, it should be broken into smaller tasks. An agent performs best on S and M tasks.
When to break a task down further:
- It would take more than one focused session (roughly 2+ hours of agent work)
- You cannot describe the acceptance criteria in 3 or fewer bullet points
- It touches two or more independent subsystems (e.g., auth and billing)
- You find yourself writing "and" in the task title (a sign it is two tasks)
Output Files
- Plan document: Save the implementation plan to
tasks/plan.md. This is always a markdown file — design decisions, risks, and open questions don't map cleanly onto individual tracker issues. - Task list: Record each task in the task list target (defined below).
Create the tasks/ directory if it does not exist.
Never overwrite an incomplete plan. Before writing tasks/plan.md or tasks/todo.md, check whether they already exist and still contain unchecked tasks:
- Same work being replanned (the user asked to revise or extend this plan) → update the existing files in place.
- Different work → stop and ask. The unchecked tasks may be mid-build in another session. Do not delete, overwrite, or rename the existing files on your own; present the conflict and let the user decide (finish the old plan first, explicitly discard it, or tell you where the new plan should go).
The same rule applies to an external task list target: never bulk-close or delete another plan's open tracker items to make room for new ones.
Task List Target
The task list target is where tasks and checkpoints are recorded. It is defined once, here; every other reference in this skill defers to it.
- Default: a checklist-style markdown file at
tasks/todo.md. This is the convention the/buildcommand and other downstream tooling expect. Use it unless the project says otherwise. - External tracker: if the project's agent rules (
CLAUDE.md,AGENTS.md, etc.) or the user designate an issue tracker (e.g. GitHub Issues, Jira, Linear,bd/beads), create one tracker item per task instead of writingtasks/todo.md. Map the Step 4 structure onto the tracker's fields: acceptance criteria and verification steps in the item body, dependencies via the tracker's linking mechanism (bd dep add, "blocked by", etc.). Record Step 5 checkpoints as tracker items too, or as a checklist in the plan document if the tracker has no natural equivalent.
When using an external tracker, note it in tasks/plan.md (e.g. "Tasks tracked in Linear project FOO") so downstream steps and future sessions know where to look, and keep the plan document's Task List section as an ordered index of tracker item IDs or links rather than a duplicate checklist.
Plan Document Template
# Implementation Plan: [Feature/Project Name]
Source spec: [path to the spec this plan was generated from, e.g. SPEC.md or SPEC-<change>.md; omit if no spec]
## Overview
[One paragraph summary of what we're building]
## Architecture Decisions
- [Key decision 1 and rationale]
- [Key decision 2 and rationale]
## Task List
### Phase 1: Foundation
- [ ] Task 1: ...
- [ ] Task 2: ...
### Checkpoint: Foundation
- [ ] Tests pass, builds clean
### Phase 2: Core Features
- [ ] Task 3: ...
- [ ] Task 4: ...
### Checkpoint: Core Features
- [ ] End-to-end flow works
### Phase 3: Polish
- [ ] Task 5: ...
- [ ] Task 6: ...
### Checkpoint: Complete
- [ ] All acceptance criteria met
- [ ] Ready for review
## Risks and Mitigations
| Risk | Impact | Mitigation |
|------|--------|------------|
| [Risk] | [High/Med/Low] | [Strategy] |
## Open Questions
- [Question needing human input]
When tasks live in an external tracker, keep the Task List section above as an ordered index of tracker item IDs or links instead of a duplicate checklist.
Parallelization Opportunities
When multiple agents or sessions are available:
- Safe to parallelize: Independent feature slices, tests for already-implemented features, documentation
- Must be sequential: Database migrations, shared state changes, dependency chains
- Needs coordination: Features that share an API contract (define the contract first, then parallelize)
Common Rationalizations
| Rationalization | Reality |
|---|---|
| "I'll figure it out as I go" | That's how you end up with a tangled mess and rework. 10 minutes of planning saves hours. |
| "The tasks are obvious" | Write them down anyway. Explicit tasks surface hidden dependencies and forgotten edge cases. |
| "Planning is overhead" | Planning is the task. Implementation without a plan is just typing. |
| "I can hold it all in my head" | Context windows are finite. Written plans survive session boundaries and compaction. |
"The old tasks/plan.md is stale, I'll just replace it" |
Unchecked tasks may be mid-build in another session. Overwriting them destroys work state that exists nowhere else. Stop and ask. |
Red Flags
- Starting implementation without a written task list
- Overwriting a
tasks/plan.mdortasks/todo.mdthat still has unchecked tasks for different work, without asking - Writing
tasks/todo.mdwhen the project has designated an external tracker (or scattering tasks across both) - Tasks that say "implement the feature" without acceptance criteria
- No verification steps in the plan
- All tasks are XL-sized
- No checkpoints between tasks
- Dependency order isn't considered
Verification
Before starting implementation, confirm:
- Every task has acceptance criteria
- Every task has a verification step
- Task dependencies are identified and ordered correctly
- Tasks are recorded in the task list target (default
tasks/todo.md) - No pre-existing incomplete plan was overwritten without explicit user confirmation
- No task touches more than ~5 files
- Checkpoints exist between major phases
- The human has reviewed and approved the plan
See Also
Acceptance criteria are per-task and answer "did we build the right thing?". They sit on top of the project-wide Definition of Done, the standing bar every task clears before it counts as done. See ../../references/definition-of-done.md.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel