execute

Orchestrate plan-driven build tasks with gate-capped verification and contract auto-patching.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/sr-ai-dev/sr-harness --skill execute-sr-ai-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: execute
Source: https://github.com/sr-ai-dev/sr-harness/tree/main/skills/execute
Command: npx skills add https://github.com/sr-ai-dev/sr-harness --skill execute-sr-ai-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Execute turns a plan (or intent-derived requirements) into an end-to-end, guardrailed build workflow by orchestrating task execution, verifying outcomes, applying contract auto-patches, and producing a structured stdout report—so you don’t have to manually coordinate steps or trust unverified outputs.

Core Features & Use Cases

  • Plan-first orchestration: Normalizes inputs, validates/initializes a plan.json, and dispatches worker work according to plan structure and dependencies.
  • Configurable dispatch + verification depth: Prompts you for dispatch mode (Direct/Agent/Team) and verify depth (Light/Standard/Thorough) and applies gate-based verification accordingly.
  • Deterministic orchestration with resumability: Treats plan.json as the ledger, skips tasks already done, enforces ceilings, and supports idempotent restart behavior.
  • Contracts mismatch auto-patching: When worker outputs indicate contract/interface drift, auto-edits contracts.md (without user confirmation) and logs the change to audit.md.
  • Coverage-driven verification and reporting: Runs unified verification, performs gap re-dispatch when citations are missing, and prints an ordered 8-section report to stdout.

Quick Start

Ask the AI to run execute with your plan directory by saying: run execute in the spec folder that contains plan.json or requirements.md, and choose Direct dispatch and Standard verify depth.

Frequently Asked Questions about execute

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate task dispatch from a plan.json file into verified code?

To orchestrate task dispatch from a plan.json file, use a plan-driven workflow that normalizes inputs, dispatches build tasks to workers, and verifies sub-requirements with gate-capped checks. It treats plan.json as a ledger, ensuring deterministic execution and idempotent resumability.

What is contract auto-patching and how does it handle interface drift?

Contract auto-patching handles interface drift by automatically editing contracts.md when worker outputs indicate mismatches, without requiring user confirmation. It logs every change to audit.md to maintain a deterministic audit trail of the modifications.

How do I start a plan-driven build workflow with requirements verification?

To start a plan-driven build workflow, run the orchestration skill in the spec folder containing plan.json or requirements.md. You will be prompted to select a dispatch mode (Direct, Agent, or Team) and a verification depth (Light, Standard, or Thorough).

Can I resume an interrupted task ledger workflow without polling for completion?

Yes, you can resume an interrupted task ledger workflow idempotently without polling for completion. The orchestration process skips tasks already marked done in plan.json, enforces dispatch ceilings, and safely restarts from the last recorded state.

What dispatch modes and verification depths are available for CI-style gate checks?

For CI-style gate checks, the available dispatch modes are Direct, Agent, and Team, while verification depths include Light, Standard, and Thorough. These options configure gate-capped checks to verify sub-requirements and enforce coverage-driven gap re-dispatch.

When should I avoid automated contract verification and task dispatch orchestration?

You should avoid automated contract verification and task dispatch orchestration when your coding session lacks a structured intent or requirements spec, as the workflow requires a plan.json ledger to safely perform tool-bound mutations and produce an ordered status report.