kastheco

Coordinate guarded, headless software-delivery work through the Kasmos MCP server. Use when Codex Desktop or an OpenClaw agent needs to research, plan, implement, monitor, recover, or report on a code or configuration change managed by Kasmos, including when a Workboard card should track a Kasmos task. Do not use for ordinary operational campaign work such as finding jobs, ranking leads, outreach, or filling applications unless the request is to change the software that performs that work.

Use when acting as the kasmos architect agent - decomposing planner specs into implementation waves, coder-ready tasks, and architecture metadata.

Use when acting as the kasmos master agent — performing holistic readiness review inside the task worktree after reviewer approval.

Use when you are the reviewer agent — checking correctness, spec compliance, and code quality on an implementation branch. Consolidates requesting-code-review + receiving-code-review + review prompt template.

Load when you are the coder agent — implementing tasks from a kasmos plan. Consolidates TDD, debugging, verification, shared worktree safety, and reviewer feedback handling into one skill.

Load when writing implementation plans for kasmos-managed projects. Consolidates brainstorming + writing-plans. Covers design exploration, plan format, and signaling.

Use when acting as the kasmos fixer agent — debugging issues, investigating failures, fixing stuck task states, cleaning up stale resources, and triaging loose ends.

Use when you need orientation on kasmos plan lifecycle, signal mechanics, or mode detection — NOT for role-specific work (use kasmos-planner, kasmos-coder, kasmos-reviewer, or kasmos-custodian instead)

Use when performing code search, refactoring, file transformations, diffing, string replacement, structured data processing, spell checking, or codebase metrics — or when about to reach for grep, sed, awk, find, diff, or wc.

Use when acting as the kasmos architect agent - decomposing planner specs into implementation waves, coder-ready tasks, and architecture metadata.

Use when an agent needs exact `kas` command syntax, flags, lifecycle transitions, or troubleshooting for task/instance/skills/setup/check/serve workflows.

Load when you are the coder agent — implementing tasks from a kasmos plan. Consolidates TDD, debugging, verification, shared worktree safety, and reviewer feedback handling into one skill.

Use when acting as the kasmos fixer agent — debugging issues, investigating failures, fixing stuck task states, cleaning up stale resources, and triaging loose ends.

Use when you need orientation on kasmos plan lifecycle, signal mechanics, or mode detection — NOT for role-specific work (use kasmos-planner, kasmos-coder, kasmos-reviewer, or kasmos-custodian instead)

Use when acting as the kasmos master agent — performing holistic final review across the merged implementation, plan, and verification evidence.

Load when writing implementation plans for kasmos-managed projects. Consolidates brainstorming + writing-plans. Covers design exploration, plan format, and signaling.

Use when acting as the kasmos architect agent - decomposing planner specs into implementation waves, coder-ready tasks, and architecture metadata.

Load when you are the coder agent — implementing tasks from a kasmos plan. Consolidates TDD, debugging, verification, shared worktree safety, and reviewer feedback handling into one skill.

Use when acting as the kasmos fixer agent — debugging issues, investigating failures, fixing stuck task states, cleaning up stale resources, and triaging loose ends.

Use when you need orientation on kasmos plan lifecycle, signal mechanics, or mode detection — NOT for role-specific work (use kasmos-planner, kasmos-coder, kasmos-reviewer, or kasmos-custodian instead)

Use when acting as the kasmos master agent — performing holistic readiness review inside the task worktree after reviewer approval.

Load when writing implementation plans for kasmos-managed projects. Consolidates brainstorming + writing-plans. Covers design exploration, plan format, and signaling.

Use when you are the reviewer agent — checking correctness, spec compliance, and code quality on an implementation branch. Consolidates requesting-code-review + receiving-code-review + review prompt template.

Use when the user asks for a production-readiness audit, project audit, kascheck, or runs /kascheck:audit. Spawns parallel subagents to assess security, code quality, infrastructure, and testing, then produces a scored report with severity-tagged findings and remediation effort estimates. Especially useful for vibe-coded/AI-generated projects.

Bidirectional bridge between ClickUp and spec-kitty feature specs. Use when the user mentions ClickUp tasks, CU- IDs, spec-kitty features, creating tasks in ClickUp, importing ClickUp context into specs, or exporting spec-kitty specs to ClickUp. Provides /specup.setup, /specup.new, /specup.import, and /specup.export commands.

This skill should be used when the user mentions "ClickUp task", "CU-xxx", "task workflow", "clickup integration", or when working with task plugin commands (/task:start, /task:done, /task:merge, /task:status, /task:new). Provides workflow patterns for ClickUp task management integrated with kas.