idh

Help the author select a target journal for a paper. This is a strategic decision combining scholarly values, career constraints, and practical fit.

Add phase to end of current milestone in roadmap

Generate tests for a completed phase based on UAT criteria and implementation

Capture idea or task as todo from current conversation context

Audit milestone completion against original intent before archiving

List pending todos and select one to work on

Archive accumulated phase directories from completed milestones

Archive completed milestone and prepare for next version

Systematic debugging with persistent state across context resets

Gather phase context through adaptive questioning before planning

Execute all plans in a phase with wave-based parallelization

Diagnose planning directory health and optionally repair issues

Show available GSD commands and usage guide

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

Join the GSD Discord community

Surface Claude's assumptions about a phase approach before planning

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

Start a new milestone cycle — update PROJECT.md and route to requirements

Initialize a new project with deep context gathering and PROJECT.md

Create context handoff when pausing work mid-phase

Create phases to close all gaps identified by milestone audit

Create detailed phase plan (PLAN.md) with verification loop

Check project progress, show context, and route to next action (execute or plan)

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents

Reapply local modifications after a GSD update

Remove a future phase from roadmap and renumber subsequent phases

Research how to implement a phase (standalone - usually use /gsd:plan-phase instead)

Resume work from previous session with full context restoration

Switch model profile for GSD agents (quality/balanced/budget)

Configure GSD workflow toggles and model profile

Update GSD to latest version with changelog display

Retroactively audit and fill Nyquist validation gaps for a completed phase

Validate built features through conversational UAT

Post-task wrap-up. Reflects on completed work, updates project state, cleans up branches.

End-of-day session wrap-up. Pushes branches, runs tests, refreshes STATE, offers autonomous session.

Project rules and conventions for the Imperial Dragon workflow. Auto-invoked at session start to establish behavioral constraints: worktree isolation, git discipline, coding standards, and STATE.md format.

Repo healthcheck — git hygiene, test status, and deep freshness verification of status/directive docs. Gracefully degrades when project-specific conventions (git-erg tickets, STATE.md, etc.) are absent.

Write, update, or sweep persistent memory. Enforces list caps, TTLs, and staleness criteria.

Create a ticket as a handoff document with required sections for TDD workflow.

Run Imperial Dragon batch across multiple tickets. Picks targets, manages waves, enforces isolation. Always autonomous — never merges.

When writing a Related Work section (or any paragraph with non-trivial citations) — produce an author's due-diligence note for one cited paragraph of a manuscript. Seven required sections: relevance, history-of-science context, cited works (detailed), related-but-not-cited (justified), methods, author-verification checklist, formal bibliography with DOI/URL. Deep-researched with snowballing and grey-literature policy; fresh each invocation.

Simulated peer review panel for manuscript prose. Spins discipline-specific agents for multi-perspective review.

Multi-perspective code review with parallel agents. Covers correctness, consistency, scope, red team, and doc propagation.

Begin work on a ticket. Creates worktree, writes first test, transitions to Execute phase.

Check a branch's diff against project rules. Mechanical-first — runs hygiene tests + grep ratchet before falling back to LLM. Emits suggested tests for any semantic finding so the LLM surface shrinks over time.

Anti-rubber-stamp merge gate. Validates every ticket exit criterion and every review comment against the actual diff. Emits APPROVED / REROLL / ESCALATE with explicit evidence. Never merges.

Run the full per-PR verification loop (adherence + review + review-pr + simplify), then gate through /verify-gate. Bounces the PR for at most one retry. Never merges.

5 hooks across 3 events