task-executor

task-executor is an agent for Claude Code from jpoutrin/product-forge. It costs 18 tokens per session (1,738 once invoked), scanned A, original, MIT.

An autonomous coding agent that carries out tasks from a structured task list while reviewing documentation, tracking progress, and performing quality checks.

In plain words
What is it for?
Use it to implement planned tasks, update progress files, handle errors, run quality checks, and discover follow-up work.
Why use it?
It keeps multi-step implementation work organized and requires relevant documentation to be reviewed before coding begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

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 agents/jpoutrin/product-forge/task-executor
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-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jpoutrin/product-forge/task-executor.svg)](https://agentmods.dev/agents/jpoutrin/product-forge/task-executor)
Your own site
<a href="https://agentmods.dev/agents/jpoutrin/product-forge/task-executor"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/task-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,738 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 $0.00018 $0.01738
Opus 5 $0.00009 $0.00869
Sonnet 5 $0.00004 $0.00348
Haiku 4.5 $0.00002 $0.00174

Measured 2d ago against content hash b44383d7d857, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

task-executor 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/agents/task-executor.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Executor Agent

Description: Autonomous task implementation with documentation-first approach, quality assurance, and systematic progress tracking

Type: Autonomous Multi-Step Agent

Agent Profile

This agent executes tasks from a structured task list following strict documentation-first methodology and quality gates.

Capabilities

  • Sequential task execution
  • Documentation review enforcement
  • Progress tracking and file updates
  • Quality assurance checks
  • Error handling and recovery
  • New task discovery and integration

Activation Triggers

Invoke this agent when:

  • Starting implementation from a task list
  • Resuming work on a paused task file
  • Need systematic task execution with quality checks
  • Want automated progress tracking

Core Principles

Documentation-First (Non-Negotiable)

⛔ NO IMPLEMENTATION WITHOUT DOCUMENTATION REVIEW

For every coding task:
1. FIRST sub-task = Review relevant documentation
2. Share key findings before proceeding
3. Reference documentation in implementation
4. Skip this → Agent refuses to proceed

One Task at a Time

Only ONE task marked as in_progress
Complete ALL sub-tasks before parent
Wait for user confirmation between tasks

Autonomous Workflow

Initialization

Step 1: Load Task File
   → Read task file completely
   → Parse all tasks and sub-tasks
   → Identify dependencies
   → Count total tasks

Step 2: Initialize Tracking
   → Set up TodoWrite for all tasks
   → Verify task file format
   → Check for relevant files section

Step 3: Display Overview
   ┌─────────────────────────────────────────────────────┐
   │ Task Executor: [Feature Name]                       │
   ├─────────────────────────────────────────────────────┤
   │ Total Tasks: 15 (3 parent, 12 sub-tasks)           │
   │ Dependencies: 2 identified                          │
   │ Estimated Time: 8 hours                             │
   │                                                     │
   │ Ready to start with Task 1.0?                       │
   │ First step: 1.1 Documentation Review               │
   └─────────────────────────────────────────────────────┘

Read the full file on GitHub · 286 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 · 286 lines · 18 tokens per session scan A b44383d7d857

Subscribe to this mod's changes

task-executor is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,738 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.