spec-execute

A command for carrying out one selected task from an approved software specification and marking that task complete.

In plain words
What is it for?
Use it to load the relevant specification and project guidance, implement a single task, run the necessary checks, and update the task list.
Why use it?
It keeps implementation focused on the agreed requirements and prevents unrelated specification tasks from being changed at the same time.

Command 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 commands/pimzino/claude-code-spec-workflow/spec-execute
Clone the repo
git clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflow

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 1,693 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 $0.00000 $0.01693
Opus 5 $0.00000 $0.00847
Sonnet 5 $0.00000 $0.00339
Haiku 4.5 $0.00000 $0.00169

Measured yesterday against content hash 0e43dec6f49a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-execute 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.

.claude/commands/spec-execute.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Execute Command

Execute specific tasks from the approved task list.

Usage

/spec-execute [task-id] [feature-name]

Phase Overview

Your Role: Execute tasks systematically with validation

This is Phase 4 of the spec workflow. Your goal is to implement individual tasks from the approved task list, one at a time.

Instructions

Agent-Based Execution (Recommended): If the spec-task-executor agent is available, use it for optimal task implementation:

Use the spec-task-executor agent to implement the specified task for the {feature-name} specification.

The agent should:
1. Load all specification context from .claude/specs/{feature-name}/
2. Load steering documents from .claude/steering/ (if available)  
3. Implement ONLY the specified task
4. Follow all project conventions and leverage existing code
5. Mark the task as complete in tasks.md
6. Provide a completion summary

Context files to load:
- .claude/specs/{feature-name}/requirements.md
- .claude/specs/{feature-name}/design.md
- .claude/specs/{feature-name}/tasks.md  
- .claude/steering/product.md (if exists)
- .claude/steering/tech.md (if exists)
- .claude/steering/structure.md (if exists)

Task to implement: {task-id}

Manual Execution (Fallback): If the agent is not available, follow this process:

  1. Prerequisites

    • Ensure tasks.md exists and is approved
    • Load the spec documents from .claude/specs/{feature-name}/:
      • Load .claude/specs/{feature-name}/requirements.md for feature requirements
      • Load .claude/specs/{feature-name}/design.md for technical design
      • Load .claude/specs/{feature-name}/tasks.md for the complete task list
    • Load all steering documents (if available):
      • Load .claude/steering/product.md for product context
      • Load .claude/steering/tech.md for technical patterns
      • Load .claude/steering/structure.md for project conventions
    • Identify the specific task to execute
  2. Process

    1. Load spec documents from .claude/specs/{feature-name}/ directory:
      • Load requirements.md, design.md, and tasks.md for complete context
    2. Execute ONLY the specified task (never multiple tasks)
    3. Implement following existing code patterns and conventions
    4. Validate implementation against referenced requirements
    5. Run tests and checks if applicable
    6. CRITICAL: Mark task as complete by changing [ ] to [x] in tasks.md
    7. Confirm task completion status to user
    8. CRITICAL: Stop and wait for user review before proceeding

Read the full file on GitHub · 197 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 · 197 lines · 0 tokens per session scan A 0e43dec6f49a

Subscribe to this mod's changes

spec-execute is a command published in the GitHub repository Pimzino/claude-code-spec-workflow (3,853 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,693 tokens. 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.