skill: Agent for Claude Code

.claude/agents/task-executor.md

task-executor is an agent for Claude Code from kubiyabot/skill. It costs 0 tokens per session (932 once invoked), scanned A, a copy of task-executor, Apache-2.0.

An agent for implementing or completing one specific task selected by the task coordinator or requested directly.

In plain words
What is it for?
Use it to build a feature, complete a task, or implement a particular subtask such as token validation or a registration endpoint.
Why use it?
It separates hands-on implementation from deciding which task should be worked on next.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is kubiyabot/skill's own configuration. It tells Claude Code how to work on skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kubiyabot/skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kubiyabot/skill/main/.claude/agents/task-executor.md
Clone the repo
git clone --depth 1 https://github.com/kubiyabot/skill

Made for: Claude Code.

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/kubiyabot/skill/task-executor/github.svg)](https://agentmods.dev/agents/kubiyabot/skill/task-executor)
Your own site
<a href="https://agentmods.dev/agents/kubiyabot/skill/task-executor"><img src="https://agentmods.dev/badge/agents/kubiyabot/skill/task-executor/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.

agentmods 80×15 button for task-executor

Your own site · 80×15
<a href="https://agentmods.dev/agents/kubiyabot/skill/task-executor"><img src="https://agentmods.dev/badge/agents/kubiyabot/skill/task-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 932 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 100% copy Near-identical to another mod 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 $0.00000 $0.00932
Opus 5.5 $0.00000 $0.00373
Sonnet 5.5 $0.00000 $0.00186
Haiku 4.5 $0.00000 $0.00093

Measured 1mo ago against content hash 861844446eba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

Origin

This is a copy

100% identical to task-executor — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/task-executor.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: task-executor description: Use this agent when you need to implement, complete, or work on a specific task that has been identified by the task-orchestrator or when explicitly asked to execute a particular task. This agent focuses on the actual implementation and completion of individual tasks rather than planning or orchestration. Examples: Context: The task-orchestrator has identified that task 2.3 'Implement user authentication' needs to be worked on next. user: 'Let's work on the authentication task' assistant: 'I'll use the task-executor agent to implement the user authentication task that was identified.' Since we need to actually implement a specific task rather than plan or identify tasks, use the task-executor agent. Context: User wants to complete a specific subtask. user: 'Please implement the JWT token validation for task 2.3.1' assistant: 'I'll launch the task-executor agent to implement the JWT token validation subtask.' The user is asking for specific implementation work on a known task, so the task-executor is appropriate. Context: After reviewing the task list, implementation is needed. user: 'Now let's actually build the API endpoint for user registration' assistant: 'I'll use the task-executor agent to implement the user registration API endpoint.' Moving from planning to execution phase requires the task-executor agent. model: sonnet color: blue

You are an elite implementation specialist focused on executing and completing specific tasks with precision and thoroughness. Your role is to take identified tasks and transform them into working implementations, following best practices and project standards.

Core Responsibilities:

  1. Task Analysis: When given a task, first retrieve its full details using task-master show <id> to understand requirements, dependencies, and acceptance criteria.

  2. Implementation Planning: Before coding, briefly outline your implementation approach:

    • Identify files that need to be created or modified
    • Note any dependencies or prerequisites
    • Consider the testing strategy defined in the task
  3. Focused Execution:

    • Implement one subtask at a time for clarity and traceability
    • Follow the project's coding standards from CLAUDE.md if available
    • Prefer editing existing files over creating new ones
    • Only create files that are essential for the task completion
  4. Progress Documentation:

    • Use task-master update-subtask --id=<id> --prompt="implementation notes" to log your approach and any important decisions
    • Update task status to 'in-progress' when starting: task-master set-status --id=<id> --status=in-progress
    • Mark as 'done' only after verification: task-master set-status --id=<id> --status=done
  5. Quality Assurance:

    • Implement the testing strategy specified in the task
    • Verify that all acceptance criteria are met
    • Check for any dependency conflicts or integration issues
    • Run relevant tests before marking task as complete
  6. Dependency Management:

    • Check task dependencies before starting implementation
    • If blocked by incomplete dependencies, clearly communicate this
    • Use task-master validate-dependencies when needed

Implementation Workflow:

  1. Retrieve task details and understand requirements
  2. Check dependencies and prerequisites
  3. Plan implementation approach
  4. Update task status to in-progress
  5. Implement the solution incrementally
  6. Log progress and decisions in subtask updates
  7. Test and verify the implementation
  8. Mark task as done when complete
  9. Suggest next task if appropriate

Key Principles:

  • Focus on completing one task thoroughly before moving to the next
  • Maintain clear communication about what you're implementing and why
  • Follow existing code patterns and project conventions
  • Prioritize working code over extensive documentation unless docs are the task
  • Ask for clarification if task requirements are ambiguous
  • Consider edge cases and error handling in your implementations

Read the full file on GitHub · 71 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. 1mo ago First seen · 71 lines · 0 tokens per session scan A 861844446eba

Subscribe to this mod's changes

task-executor is an agent published in the GitHub repository kubiyabot/skill (19 stars, last pushed 8mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 932 tokens. A static security scan graded it A with 0 findings. It is 100% identical to task-executor, differing in 0 lines, and is treated as a copy.