From checkpoint
Run a harness against a workflow — execute the harness steps on the next actionable task.
npx claudepluginhub samklevin/claude-skills --plugin checkpointThis skill is limited to using the following tools:
You are executing a harness against a workflow. The harness defines *how* to work; the workflow defines *what* to work on.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Monitors deployed URLs for regressions in HTTP status, console errors, performance metrics, content, network, and APIs after deploys, merges, or upgrades.
Provides React and Next.js patterns for component composition, compound components, state management, data fetching, performance optimization, forms, routing, and accessible UIs.
You are executing a harness against a workflow. The harness defines how to work; the workflow defines what to work on.
Parse $ARGUMENTS to get the harness name and workflow name. If not provided or ambiguous, ask.
Read:
.claude/harnesses/<harness-name>.yaml — the harness definition.claude/skills/<workflow-name>/context.yaml — workflow context.claude/skills/<workflow-name>/tasks.yaml — workflow tasksIf either file doesn't exist, tell the user and suggest how to create it.
Validate the harness — verify it has steps (non-empty list), constraints (list), done_criteria (list), and pause_between_tasks (boolean). If any required field is missing or malformed, report the issue and stop.
Find the next actionable task from tasks.yaml:
status: in-progress (resume it)status: todo whose dependencies (if any) are all donestatus: blocked that has a blocked_by reason (these need external resolution)Present the target task and the harness that will be applied. Ask for confirmation before proceeding.
If the user declines the suggested task, ask which task they'd prefer to work on, or whether to mark the current task as blocked.
For each step defined in the harness, in order:
instruction field, applying it to the current taskconstraints throughout executionUse the workflow's context.yaml learnings and decisions as background knowledge throughout.
Before marking the task complete, check each item in the harness's done_criteria:
After the task is complete:
status to done in tasks.yaml and add completion notescontext.yamlcontext.yamlIf the harness has pause_between_tasks: true:
If pause_between_tasks: false: