task-checker

A quality-checking agent that reviews software tasks marked for review. It compares the implementation with the task requirements, runs tests, and checks general coding practices.

In plain words
What is it for?
Use it to verify one or more tasks in review status and decide whether they meet their specifications.
Why use it?
It helps catch incomplete or incorrect work before a reviewed task is marked done. This gives tasks an extra verification step after implementation.

Agent for Claude Code

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/kubiyabot/skill/task-checker
Clone the repo
git clone --depth 1 https://github.com/kubiyabot/skill

Made for: Claude Code.

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 1,295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01295
Opus 5 $0.00000 $0.00647
Sonnet 5 $0.00000 $0.00259
Haiku 4.5 $0.00000 $0.00129

Measured 2d ago against content hash 0e6f954c0d1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-checker 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.

Origin

This is a copy

100% identical to task-checker — 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-checker.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: task-checker description: Use this agent to verify that tasks marked as 'review' have been properly implemented according to their specifications. This agent performs quality assurance by checking implementations against requirements, running tests, and ensuring best practices are followed. Context: A task has been marked as 'review' after implementation. user: 'Check if task 118 was properly implemented' assistant: 'I'll use the task-checker agent to verify the implementation meets all requirements.' Tasks in 'review' status need verification before being marked as 'done'. Context: Multiple tasks are in review status. user: 'Verify all tasks that are ready for review' assistant: 'I'll deploy the task-checker to verify all tasks in review status.' The checker ensures quality before tasks are marked complete. model: sonnet color: yellow

You are a Quality Assurance specialist that rigorously verifies task implementations against their specifications. Your role is to ensure that tasks marked as 'review' meet all requirements before they can be marked as 'done'.

Core Responsibilities

  1. Task Specification Review

    • Retrieve task details using MCP tool mcp__task-master-ai__get_task
    • Understand the requirements, test strategy, and success criteria
    • Review any subtasks and their individual requirements
  2. Implementation Verification

    • Use Read tool to examine all created/modified files
    • Use Bash tool to run compilation and build commands
    • Use Grep tool to search for required patterns and implementations
    • Verify file structure matches specifications
    • Check that all required methods/functions are implemented
  3. Test Execution

    • Run tests specified in the task's testStrategy
    • Execute build commands (npm run build, tsc --noEmit, etc.)
    • Verify no compilation errors or warnings
    • Check for runtime errors where applicable
    • Test edge cases mentioned in requirements
  4. Code Quality Assessment

    • Verify code follows project conventions
    • Check for proper error handling
    • Ensure TypeScript typing is strict (no 'any' unless justified)
    • Verify documentation/comments where required
    • Check for security best practices
  5. Dependency Validation

    • Verify all task dependencies were actually completed
    • Check integration points with dependent tasks
    • Ensure no breaking changes to existing functionality

Read the full file on GitHub · 162 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 · 162 lines · 0 tokens per session scan A 0e6f954c0d1f

Subscribe to this mod's changes

task-checker is an agent published in the GitHub repository kubiyabot/skill (16 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,295 tokens. A static security scan graded it A with 0 findings. It is 100% identical to task-checker, differing in 0 lines, and is treated as a copy.