Pantheon Deepwork — Productivity skill for Claude Code
Start a heavy multi-phase task with persisted checkpoints, phased specialist dispatch, and Themis review gates.
How to install Pantheon Deepwork
Installs to ~/.claude/skills/ils15-pantheon-legacy-pantheon-deepwork/SKILL.md
mkdir -p ~/.claude/skills/ils15-pantheon-legacy-pantheon-deepwork && curl -fsSL https://raw.githubusercontent.com/ils15/pantheon-legacy/HEAD/commands/pantheon-deepwork.md -o ~/.claude/skills/ils15-pantheon-legacy-pantheon-deepwork/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Pantheon Deepwork does
description: "Start a heavy multi-phase task with persisted checkpoints, phased specialist dispatch, and Themis review gates. Progress saved to .pantheon/deepwork/ for resumability. Usage: /pantheon-deepwork" agent: "zeus"
/pantheon-deepwork — Heavy Task Workflow
**What:** Starts a structured, checkpointed workflow for complex multi-step tasks. Progress is persisted to `.pantheon/deepwork//` so work can resume if interrupted. Each phase is gated by Themis review.
When t
Alternatives in Productivity
- Claude Hud — A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progr 14k ★
- Gov Metrics — Governance metrics — measure whether the gates actually work 83 ★
- Agent Sop — Human-gated, capability-slotted collaboration workflow (SOP) for coding agents — discovered rosters, condition 70 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Deepwork
Start a heavy multi-phase task with persisted checkpoints, phased specialist dispatch, and Themis review gates
J Execute Plan
Execute a written implementation plan task-by-task with verification gates — inline batches or a fresh subagen
Ship It Skill
Cross-platform coding-agent skill (Claude Code / OpenCode / omp): disciplined phased workflow with mandatory a
Graph Ship
Run a named playbook end to end - execute its nodes, honor its gates, dispatch each agent with the skills its
Session Note
Save a session summary for human resumability
Router Report
Generate the router usage report for a window (default 7 days; also 1d / yesterday), scoring the three north-s
Related Agents
Shadowcat Code Reviewer
Read-only code-quality review — bugs, logic errors, security, project-convention adherence, simplification and
Robium Architect
Robotics application architect. Use PROACTIVELY at the start of any new robotics application to run the heavy
Hatch3r Handoff Loader
Session-start agent that surfaces active handoff documents from .hatch3r/handoffs/active/. Use at the beginnin