A command that turns a project plan into an ordered list of development tasks. TDD, or test-driven development, means writing tests before the code they check.

Use it after planning a feature or larger project to create a 20–30 task breakdown, either with standard test-first work or with HTML mockup tasks first.

It makes a large feature easier to implement by defining acceptance checks, task sizes, dependencies, and which tasks can be done in parallel.

tasks — Command by marcusgoll

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.

agentmods

npx agentmods add commands/marcusgoll/spec-flow/tasks

Clone the repo

git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 7,943 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00021	$0.07943
Opus 5	$0.00010	$0.03972
Sonnet 5	$0.00004	$0.01589
Haiku 4.5	$0.00002	$0.00794

Measured 2d ago against content hash 92767d56d701, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/phases/tasks.md · 1,041 lines

How it starts

The opening of the file, as written. The whole thing — 1,041 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tasks — Task Breakdown Generator (Thin Wrapper)

v11.0 Architecture: This command spawns the isolated tasks-phase-agent via Task(). All task breakdown logic runs in isolated context.

Active Feature: !ls -td specs/[0-9]*-* 2>/dev/null | head -1 || echo "none"

Interaction State: !cat specs/*/interaction-state.yaml 2>/dev/null | head -10 || echo "none"

Architecture (v11.0 - Phase Isolation):

/tasks → Task(tasks-phase-agent) → tasks.md with TDD structure

Agent responsibilities:

Read plan.md and spec.md
Generate 20-30 tasks with acceptance criteria
Follow TDD Red-Green-Refactor pattern
Calculate task sizes (XS/S/M/L)
Identify dependencies and parallel-safe tasks

Mode detection:

Epic workflows: Sprint breakdown with dependency graph
Feature workflows: Tasks organized by user story priority
UI-first mode (--ui-first): Mockup tasks before implementation

Flags:

--ui-first: Generate HTML mockup tasks first
--standard: Standard TDD task generation
--no-input: Non-interactive mode for CI/CD

Workflow position: spec → clarify → plan → tasks → implement → optimize → ship

Legacy Context (for agent reference)

<legacy_context> Current git status: !git status --short | head -10

Current branch: !git branch --show-current

Feature spec exists: Auto-detected (epics//epic-spec.md OR specs//spec.md)

Plan exists: Auto-detected (epics//plan.md OR specs//plan.md) </legacy_context>

Step 0: WORKFLOW DETECTION

Detect workflow using centralized skill (see .claude/skills/workflow-detection/SKILL.md):

Run detection: bash .spec-flow/scripts/utils/detect-workflow-paths.sh
Parse JSON: Extract type, base_dir, slug from output
If detection fails (exit code != 0): Use AskUserQuestion fallback
Set paths:
- Feature: SPEC_FILE="${BASE_DIR}/${SLUG}/spec.md"
- Epic: SPEC_FILE="${BASE_DIR}/${SLUG}/epic-spec.md"
- Common: PLAN_FILE="${BASE_DIR}/${SLUG}/plan.md", TASKS_FILE="${BASE_DIR}/${SLUG}/tasks.md"

Read the full file on GitHub · 1,041 lines

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.

2d ago First seen · 1,041 lines · 0 tokens per session scan A 92767d56d701

Subscribe to this mod's changes

tasks is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 7,943 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Frontend Testing Writing and docs ai-agents ai-assisted-development ai-workflows automation bash claude

tasks

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/tasks — Task Breakdown Generator (Thin Wrapper)

Legacy Context (for agent reference)

Step 0: WORKFLOW DETECTION

What this file has done since we first saw it

Other commands, from other repositories

quick-fix

review

usage-add

pi-code-review

milestone-list

setup