resume

Resumes an approved project plan from current state with swarm identity reconciliation.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/ZaxbyHub/ragappv3 --skill resume-zaxbyhub
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: resume
Source: https://github.com/ZaxbyHub/ragappv3/tree/main/.opencode/skills/resume
Command: npx skills add https://github.com/ZaxbyHub/ragappv3 --skill resume-zaxbyhub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Continuing work on an existing project plan risks acting on stale context, mismatched swarm identities, or outdated cached agent data, which can corrupt execution state. ## Core Features & Use Cases - Plan State Detection: Reads .swarm/plan.md to determine whether to resume an existing plan or start a new project via MODE: CLARIFY. - Swarm Identity Reconciliation: Detects mismatches between the plan's Swarm field and the active swarm id, purges stale memory blocks and SME cache entries, and updates plan.md and context.md accordingly. - New Project Risk Baseline: Runs complexity_hotspots, todo_extract, and sbom_generate to build a risk map, capture technical debt, and record a dependency inventory for new projects. - Use Case: An agent restarts a session where the plan was created under a different swarm; the protocol clears stale identity context, informs the user, and resumes at the current task safely. ## Quick Start Resume the current project from .swarm/plan.md and reconcile any stale swarm context before continuing.

Frequently Asked Questions about resume

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

FAQPage Schema
How do I resume an existing project plan safely?▼

Read the Swarm field in .swarm/plan.md and compare it to the active swarm id. If they match or the field is missing, resume at the current task; if they differ, update the field and clear stale context before continuing.

What happens when the plan's swarm id differs from the active swarm?▼

The plan.md and context.md Swarm fields are updated to the active swarm id, memory blocks referencing the other swarm's identity are purged, and the SME Cache section is deleted. The user is informed that stale context was cleared before resuming.

What happens if no plan file exists when resuming?▼

If .swarm/plan.md does not exist, the project is treated as new and the workflow proceeds to MODE: CLARIFY. Discovery tools then run to build a risk and dependency baseline.

Which tools run when starting a new project?▼

The complexity_hotspots tool runs over 90 days to generate a risk map, todo_extract optionally captures existing technical debt, and sbom_generate with scope 'all' saves a baseline dependency inventory to .swarm/evidence/sbom/.

Why is stale context cleared when switching swarms?▼

Memory blocks and SME cache entries from another swarm reference a different identity and agent set, which would corrupt execution. Identity must come only from the current system prompt, so stale entries are purged before resuming.