claude

ship-flow

Ship-focused development pipeline. SHAPE once with captain, then agents autonomously plan → execute → ship.

0 on GitHubby Kentv0.9.0Apache-2.0updated 3 months ago
/

Plugin ship-flow from marketplace spacedock-workflows in iamcxa/spacedock-workflows. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (22)

  • add-todos

    Use when capturing ship-flow todo ideas, rabbit holes, or quick captain notes without starting a full shape cycle.

  • codex-gate

    Use when verify stage wants an adversarial cross-model second opinion on the execute diff before PR-create. Wraps `codex exec` (OpenAI Codex CLI) with a ship-flow-tuned locked prompt focused on failure classes Claude reviewers historically miss (schema/migration, silent failure, concurrency, regex b

  • distill-reference

    Use when mining an external workflow/plugin/source tree for ship-flow improvement candidates while preserving hermetic runtime boundaries.

  • doc-sync

    Use when syncing Ship Flow plugin documentation after stage skill, invariant, workflow, shell primitive, or release changes.

  • domain-registry

    Use when ship-design, schema-designer, or intent-match-verifier needs domain registry routing or knowledge-module lookup context.

  • harvest-decide

    Use when adjudicating pending success-mode / failure-mode harvest candidates emitted by ship-review Step 4.5 — decide promote/merge/draft/discard per candidate and stamp the ledger. Closes the T1-3 success-mode lifecycle invariant.

  • memory-cleanup

    Use when the project MEMORY.md grows past its budget (SessionStart size warning, or captain notices bloat) — measures against the budget, classifies entries against the 6-gate rubric, proposes a prune/consolidate matrix for captain review, and applies after approval.

  • science-officer-em

    Use when the captain asks for Science Officer, 科學官, SO, or EM engineering judgment on ship-flow work, risk trade-offs, scope challenge, worker stewardship quality, or a proceed/narrow/return/block/costly_no call.

  • ship-design

    Use when shape finds UI, domain, contract, interface, visual ambiguity, affects_ui, design_required, or no design reference before plan.

  • ship-epic

    Use when a clean session must run a project-intake epic's born-sharped children to PRs in dependency order — after /ship-project or shape-confirm instantiated an epic + depends-on children and they must be dispatched wave-by-wave, not one at a time. Triggers: 'run the epic', 'ship-epic', orchestrate

  • ship-execute

    Use when ship-flow needs execute-stage implementation from an approved plan, including wave tasks, blocked work, or PR feedback re-entry. Layer A delegation: superpowers:subagent-driven-development owns wave dispatch discipline.

  • ship-onboard

    Use when adopting ship-flow in a repo after workflow scaffolding exists, or when onboarding needs initial PRODUCT and ROADMAP context.

  • ship-plan

    Use when writing a ship-flow plan for a shaped entity, especially implementation tasks, TDD needs, runtime commands, or scope anchoring. Layer A delegation: superpowers:writing-plans owns plan authoring; ship-flow:test-driven-development owns fallback TDD contracts.

  • ship-project

    Use when the captain hands a planned tracker project (a Linear project ref — name/URL/id) and wants it instantiated as committed pipeline entities + a wave/parallel plan in one shot, instead of hand-shaping each issue. Fetches + filters the project's issues, builds a cut-project contract, and instan

  • ship-review

    Use when verify passed and ship-flow needs review, PR readiness, PR body drafting, or canonical docs sync. Layer A delegation: pr-review-toolkit:review-pr owns PR review persona philosophy.

  • ship-runtime-detect

    Use when ship-flow needs runtime detection for test, build, typecheck, lint, dev, or formatter commands across project stacks.

  • ship-shape

    Use when shaping vague, complex, or ambiguous ship-flow requests into a Shape Up pitch, including `/shape`, discussion, or skill-authoring work.

  • ship-verify

    Use when verifying execute output before ship, including `/verify`, `/ship`, live worktree checks, UI DCs, e2e, reviewer panel, or NIT fixes. Layer A delegation: e2e-pipeline and ship-flow:ui-verify own UI DC verification; reviewer personas own haiku review.

  • ship

    Use when `/ship` should run ship-flow for an entity id or good-enough raw requirement; vague inputs need shape clarification.

  • test-driven-development

    Use when ship-flow plan, execute, or verify needs TDD, test-first discipline, or RED-before-GREEN evidence for code-bearing tasks.

  • ui-verify

    Use when ship-flow needs UI verify coverage for render fidelity, selectors, design tokens, computed CSS, dimensions, or handoff targets.

  • verify-reviewer-panel

    Use when ship-verify needs a reviewer panel fallback, external reviewer, silent failure reviewer, domain expert, or file:line findings lens.

Subagents (1)

  • science-officer-em

    Use when the captain asks for Science Officer, 科學官, SO, or EM engineering judgment on ship-flow work, risk trade-offs, scope challenge, worker stewardship quality, or a proceed/narrow/return/block/costly_no call.

Hooks (2)

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/hooks/warn-direct-read.js"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/warn-state-drift.sh"

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Maintain ship-flow?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted