continuity-test

Validate three-session handoff continuity with HANDOFF.md chaining and gating hooks.

Updated Jun 4, 2026
One-click install
npx skills add https://github.com/Kohlex/autopilot-plugin --skill continuity-test
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: continuity-test
Source: https://github.com/Kohlex/autopilot-plugin/tree/main/skills/continuity-test
Command: npx skills add https://github.com/Kohlex/autopilot-plugin --skill continuity-test

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run a 3-session continuity smoke test on MockPerfect (or another sandbox). Validates HANDOFF.md authoring, /confident-handoff ≥95% loop, cross-session resume, K/A/D archive, conventional-commit hook, and budget-watcher hook firing. Document-only — no code, no TDD, no per-session worktrees. Invoke as /continuity-test mockperfect [--resume].

Core Features & Use Cases

  • Validates end-to-end continuity of AutoPilot's multi-session handoff across three sessions.
  • Ensures HANDOFF.md chain integrity, cross-session resume capability, and archival workflow with K/A/D classification.
  • Verifies gating hooks (conventional-commit, budget-watcher) and confidence thresholds for regression testing.

Quick Start

Run the continuity-test to execute three-session smoke testing against MockPerfect in a sandbox environment.

Frequently Asked Questions about continuity-test

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

FAQPage Schema
How do I test multi-session handoff continuity in AutoPilot?

Multi-session handoff continuity is validated by running a three-session smoke test that verifies HANDOFF.md chain integrity, cross-session resume capability, and K/A/D archival workflow against a sandbox environment.

How does the budget-watcher trigger work during session handoff?

The budget-watcher triggers fire during session transitions as part of the continuity test, verifying that budget gating hooks activate correctly alongside conventional-commit enforcement across the three-session workflow.

Can I resume a failed continuity test from a specific session?

Cross-session resume capability is supported by invoking the continuity test with the --resume flag, allowing you to restart the smoke test from the interrupted session without re-running the entire workflow.

Does the continuity test require writing code or setting up per-session worktrees?

The continuity test is document-only and requires no code writing, no TDD, and no per-session worktrees, focusing solely on validating HANDOFF.md authoring and archival workflow in a sandbox environment.

What is the /confident-handoff threshold for regression testing?

The confident-handoff threshold requires a minimum 95% confidence loop, which the continuity test enforces as a gate to ensure handoff quality before proceeding to the next session in the workflow.

What limitations exist when validating handoff workflows with MockPerfect?

The continuity test validates document-only workflows in sandbox environments and does not execute code, run TDD cycles, or create per-session worktrees, limiting its scope to handoff chain and archive verification.