verify-against-plan

Compare implementation against plan artifacts and report gaps to a markdown file.

9|1|Updated Jan 8, 2026

Search Tags:#automation #completeness #artifacts #plan #verify #code-review

Ready to run

npx skills add https://github.com/conn-castle/agent-layer --skill verify-against-plan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: verify-against-plan
Source: https://github.com/conn-castle/agent-layer/tree/main/internal/templates/skills/verify-against-plan
Command: npx skills add https://github.com/conn-castle/agent-layer --skill verify-against-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compare the current implementation and working tree against a plan/task/context artifact set, then report completeness gaps, regressions, missing tests or docs, and scope drift.

Core Features & Use Cases

Completeness verification: compares code, docs, and tests to the plan artifacts (plan/task/context) and reports gaps.
Multi-agent review workflow: facilitates Plan reader, Implementation reviewer, and Verifier reviewer roles to assess completeness and adherence.
Documentation and memory updates: flags missing documentation or tests and suggests remediation.
Use Case: a repo with .agent-layer/tmp containing the latest plan/task/context artifacts can be evaluated to generate a verify-against-plan report.

Quick Start

Run the verify-against-plan tool to generate a completeness report for the latest plan/task/context artifacts.

Frequently Asked Questions about verify-against-plan

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

FAQPage Schema

How do I verify code completeness against a plan artifact set?▼

You can verify code against a plan by comparing the working tree to plan, task, and context artifacts. The tool scopes to the latest artifact versions and flags missing tests, documentation gaps, and scope drift.

Does verification modify my code when checking for scope drift?▼

No, checking for scope drift does not modify your code. The process generates a deterministic completeness report to .agent-layer/tmp/verify-against-plan.<run-id>.report.md without altering your working tree.

What is the best way to automate completeness checks for plan artifacts?▼

Automating completeness checks for plan artifacts involves running a verification process that scopes to plan/task/context artifacts. It automatically reports regressions, missing tests, and scope drift without modifying the codebase.

Can I use a multi-agent review workflow to assess implementation adherence?▼

Yes, assessing implementation adherence can be done using a multi-agent review workflow. The process facilitates Plan reader, Implementation reviewer, and Verifier reviewer roles to evaluate completeness and adherence to the plan artifacts.

Do I need specific artifacts in my repo to generate a completeness report?▼

Yes, generating a completeness report requires a repository containing the latest plan, task, and context artifacts within the .agent-layer/tmp directory. The verification scopes specifically to these artifacts to evaluate the working tree.