task-focus

task-focus is a skill for Claude Code from jpoutrin/product-forge. It costs 11 tokens per session (727 once invoked), scanned A, original, MIT.

A task-focus command that moves one task into an active focus area, reads its checklist, and restores its progress for the current session.

In plain words
What is it for?
Use it to start or resume a task from a file, load its checklist into a to-do list, and record when focused work began.
Why use it?
It keeps work centered on one task and avoids losing track of subtasks, progress, or where to resume.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the TodoWrite tool; mentions Claude Code.

Part of the product-design plugin — 43 skills, 8 agents shipped together

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 skills/jpoutrin/product-forge/task-focus
Any agent
npx skills add jpoutrin/product-forge --skill task-focus
Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge

Made for: Claude Code.

Or install product-design, the plugin that ships this one along with the rest of its 43 skills, 8 agents.

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.

agentmods badge for task-focus

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpoutrin/product-forge/task-focus.svg)](https://agentmods.dev/skills/jpoutrin/product-forge/task-focus)
Your own site
<a href="https://agentmods.dev/skills/jpoutrin/product-forge/task-focus"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/task-focus.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 727 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.00727
Opus 5 $0.00005 $0.00364
Sonnet 5 $0.00002 $0.00145
Haiku 4.5 $0.00001 $0.00073

Measured 2d ago against content hash 814330609620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

task-focus 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.

plugins/product-design/skills/task-focus/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task-focus

Category: Task Management

Usage

task-focus <task-file>

Arguments

  • <task-file>: Required - Path to task file to focus on

Execution Instructions for Claude Code

When this command is run, Claude Code should:

  1. Check if focus/ directory is empty (enforce one-task rule)
  2. If not empty, show current focus and ask to switch
  3. Move the specified task file to tasks/focus/
  4. Parse the task file to extract:
    • Task metadata (ID, title, status, priority)
    • All subtasks with their completion status
    • Current progress percentage
  5. Load all tasks into TodoWrite tool
  6. Update task file header with focus start time
  7. Display current progress and next incomplete subtask
  8. Show session restoration command for future use

TodoTools Loading

Convert task file format to TodoWrite format:

# File format: - [x] 1.1 Task description (2h)
# Todo format: {"id": "1.1", "content": "Task description", "status": "completed", "priority": "medium"}

# Status mapping:
# [ ] → "pending"
# [-] → "in_progress"
# [x] → "completed"
# [~] → "cancelled" (exclude from todos)

Focus Session Start

Add to task file work log:

## Work Log

### 2025-01-06 14:30 - SESSION START
- Moved to focus
- Current progress: 40%
- Next task: 2.3 Implement JWT tokens

Output Format

🎯 Focusing on: TASK-001-user-authentication.md

📊 Task Overview:
   Title: Implement User Authentication
   Progress: 40% (4/10 subtasks)
   Estimated remaining: 4.5 hours
   Dependencies: All satisfied ✅

📋 Loading tasks into TodoTools...
   ✅ Loaded 10 tasks (4 completed, 6 pending)

🚀 Next subtask:
   2.3 Implement JWT tokens (est. 2h)

💡 To resume this session later:
   task-focus tasks/focus/TASK-001-user-authentication.md

Ready to work! Use 'task-done' when completing subtasks.

Error Handling

  • If task file not found: Show available tasks with task-list
  • If focus not empty: Show current focus and confirm switch
  • If task file invalid: Run validation and show errors
  • If already in focus: Show message and continue

Read the full file on GitHub · 113 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.

  1. 2d ago First seen · 113 lines · 11 tokens per session scan A 814330609620

Subscribe to this mod's changes

task-focus is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 727 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens