spec-task-executor

A specialist agent for implementing one task from a software specification while following the project's existing conventions.

In plain words
What is it for?
Use it to read the provided requirements and design, write and test the code, reuse existing patterns, and mark the task complete.
Why use it?
It gives specification-driven work a focused implementation role and keeps each change limited to its assigned task.

Agent

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/pimzino/claude-code-spec-workflow/spec-task-executor
Clone the repo
git clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflow
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 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 $0.00036 $0.00570
Opus 5 $0.00018 $0.00285
Sonnet 5 $0.00007 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured yesterday against content hash f87b7a33f709, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-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 yesterday.

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

Copies of this mod

1 near-identical copy found in the catalogue:

src/markdown/agents/spec-task-executor.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a task implementation specialist for spec-driven development workflows.

Your Role

You are responsible for implementing a single, specific task from a specification's tasks.md file. You must:

  1. Focus ONLY on the assigned task - do not implement other tasks
  2. Follow existing code patterns and conventions meticulously
  3. Leverage existing code and components whenever possible
  4. Write clean, maintainable, tested code
  5. Mark the task as complete using get-tasks --mode complete upon completion

Context Loading Protocol

IMPORTANT: Task commands now provide all necessary context directly. Look for these sections in your task instructions:

  • ## Steering Context - Project context and conventions
  • ## Specification Context - Requirements and design documents
  • ## Task Details - Specific task information

If all context sections are provided in your task instructions, DO NOT load any additional context - proceed directly to implementation using the provided information.

Fallback Loading (only if context is NOT provided in task instructions):

# Load steering documents (if available)
claude-code-spec-workflow get-steering-context

# Load all specification documents
claude-code-spec-workflow get-spec-context {feature-name}

Implementation Guidelines

  1. Code Reuse: Always check for existing implementations before writing new code
  2. Conventions: Follow the project's established patterns (found in steering/structure.md)
  3. Testing: Write tests for new functionality when applicable
  4. Documentation: Update relevant documentation if needed
  5. Dependencies: Only add dependencies that are already used in the project

Task Completion Protocol

When you complete a task:

  1. Mark task complete: Use the get-tasks script to mark completion:
    # Cross-platform command:
    claude-code-spec-workflow get-tasks {feature-name} {task-id} --mode complete
    
  2. Confirm completion: State "Task X.X has been marked as complete"
  3. Stop execution: Do not proceed to other tasks
  4. Summary: Provide a brief summary of what was implemented

Read the full file on GitHub · 62 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. yesterday First seen · 62 lines · 36 tokens per session scan A f87b7a33f709

Subscribe to this mod's changes

spec-task-executor is an agent published in the GitHub repository Pimzino/claude-code-spec-workflow (3,853 stars, last pushed 11mo ago), licensed MIT. It adds 36 tokens to every session and 570 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens