A task planner that turns an implementation plan into an ordered task list with dependencies. It uses project specifications and planning files as its input.

Use it after creating a plan to generate tasks.md, split work into numbered tasks, record user-story links, and track task dependencies.

It makes large feature plans easier to execute and helps show which tasks are covered, blocked, or able to run in parallel.

afc:tasks — Skill for Claude Code by jhlee0409

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.

Any agent

npx skills add jhlee0409/all-for-claudecode --skill tasks

Clone the repo

git clone --depth 1 https://github.com/jhlee0409/all-for-claudecode

Made for: Claude Code.

Or install afc, the plugin that ships this one along with the rest of its 29 skills, 12 agents, 19 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jhlee0409/all-for-claudecode/tasks/github.svg)](https://agentmods.dev/skills/jhlee0409/all-for-claudecode/tasks)

Your own site

<a href="https://agentmods.dev/skills/jhlee0409/all-for-claudecode/tasks"><img src="https://agentmods.dev/badge/skills/jhlee0409/all-for-claudecode/tasks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jhlee0409/all-for-claudecode/tasks"><img src="https://agentmods.dev/badge/skills/jhlee0409/all-for-claudecode/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00012	$0.01251
Opus 5	$0.00006	$0.00626
Sonnet 5	$0.00002	$0.00250
Haiku 4.5	$0.00001	$0.00125

Measured 8d ago against content hash b8c648a17703, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

afc: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 8d 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.

skills/tasks/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/afc:tasks — Task Decomposition

Generates an executable task list (tasks.md) from plan.md. Validates coverage with a convergence-based Critic Loop.

Note: In /afc:auto, task generation runs automatically at implement start. Use this command only for standalone manual control.

Arguments

$ARGUMENTS — (optional) additional constraints or priority directives

Config Load

Read .claude/afc.config.md first. If missing: print ".claude/afc.config.md not found. Run /afc:init first." then abort.

Execution Steps

1. Load Context

From .claude/afc/specs/{feature}/:

plan.md (required) — if missing: "Run /afc:plan first."
spec.md (required), research.md (if present)

Extract from plan.md: phase breakdown, File Change Map, architecture decisions.

2. Decompose Tasks

Task Format

- [ ] T{NNN} {[P]} {[US*]} {description} `{file path}` {depends: [TXXX, ...]}

Component	Required	Description
`T{NNN}`	Yes	3-digit sequential ID
`[P]`	No	Mandatory parallel execution — no file overlap with other [P] tasks in same phase
`[US*]`	No	User Story label from spec.md
`description`	Yes	Verb-first clear description
`file path`	Yes	Primary target file
`depends:`	No	Blocking dependency list

Phase Structure

# Tasks: {feature name}
## Phase 1: Setup    — type definitions, configuration
## Phase 2: Core     — business logic, store, API
## Phase 3: UI       — components, interactions
## Phase 4: Integration & Polish — error handling, optimization

Decomposition Rules

1 task = 1 file (where possible)
Same file → sequential; different files → [P] candidate
[P] is mandatory, not optional — once marked, task MUST run in parallel
Validate [P] file overlaps: run "${CLAUDE_SKILL_DIR}/../../scripts/afc-parallel-validate.sh" .claude/afc/specs/{feature}/tasks.md
Validate DAG (no cycles): run "${CLAUDE_SKILL_DIR}/../../scripts/afc-dag-validate.sh" .claude/afc/specs/{feature}/tasks.md — abort if cycle detected
Include a verification task per testable unit
Add {config.gate} validation task at end of each Phase
No over-decomposition: skip separate tasks for single-line changes

Read the full file on GitHub · 130 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.

8d ago First seen · 130 lines · 12 tokens per session scan A b8c648a17703

Subscribe to this mod's changes

afc:tasks is a skill published in the GitHub repository jhlee0409/all-for-claudecode (7 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 1,251 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 2026-08-31.

Claude Code Planning agentic-coding ai-coding anthropic automation

eval-agents

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…

FlorianBruniaux/claude-code-ultimate-guide · 93 tokens

afc:tasks