shipguard

Plugin shipguard from marketplace shipguard in bacoco/ShipGuard. Commands read from the repo's manifest — 4 days ago.

Skills (20)

• grill-goal

  Clarify the user's intent through an in-depth dialogue, then write a standalone, verifiable Markdown goal for another AI. Use to define, write, or improve a goal without executing the work it describes.

• sg-beat-reference

  Turn a quality goal into ONE paste-ready prompt that makes a fresh agent grind builders against blind critics until the work beats a named, fetchable reference. Use when the user wants to beat a specific product, page, repo, or published piece; when they ask for a prompt to hand another agent; or wh

• sg-change-report

  Use after visual runs, screenshot capture, frontend PRs, or before stakeholder review — creates the durable ShipGuard before/after report for UI-visible changes.

• sg-code-audit

  Use when code has changed and needs a bug audit before shipping — after a feature, before a PR, or on demand for any scoped path. Reports structured findings by default; source fixes require an explicit --fix opt-in.

• sg-communication-memory

  Study authorized Claude/Codex conversations for contextual jargon, frustration, repetition and misunderstandings; review changes since the last study and suggest improvements for both human and AI, or consult private memory to interpret ambiguous language. Use for requested dialogue studies and prog

• sg-gauntlet

  Deprecated alias for sg-beat-reference. Use only when the user explicitly invokes the former sg-gauntlet name; route the request to the canonical skill that builds a bounded builder-versus-critic prompt against a named, fetchable reference.

• sg-improve

  Use after an audit, visual run, or debugging session when learnings should be captured — records local hints and mistakes, and proposes sanitized improvement issues. Use --prompt-audit for an explicit read-only review of selected instructions.

• sg-logic-audit

  Audit a workflow, state machine, retry policy, transaction, or non-trivial algorithm against declared contracts and invariants. Use when local code may look valid but end-to-end logic, ordering, conservation, idempotency, termination, authorization, or boundary behavior needs absolute correctness ch

• sg-mission-lock

  Keep the agent on the outcome the user asked for without re-asking permission: answer simple questions briefly, restate work requests visibly, treat a yes as authority for every reversible step until the next no, and ask first only for accounts and their rights, secrets, destructive actions and prod

• sg-model-scope-test

  Run read-only behavioral probes against one or more selectable agent models and reasoning efforts, then report whether each configuration preserves the user's authorized delta. Use only when the user explicitly requests model or effort comparisons, scope probes, or a Strict Delta Lock test; never se

• sg-pre-review

  Review a proposed change before coding: find reusable interfaces, trace their actual consumers, and recommend the smallest justified change. Explicit invocation, report-only; not a bug audit or a goal interview.

• sg-process-check

  Use after editing backend or pipeline code, before shipping, or when asked whether a diff changes observable behavior — verifies before/after process behavior without requiring the stack to run.

• sg-record

  Use when a user flow should be captured by demonstration — records browser interactions with Playwright into a replayable ShipGuard visual test manifest.

• sg-scout

  Use when looking for techniques to improve ShipGuard itself — researches GitHub and similar tools and files scored proposals from the ShipGuard checkout.

• sg-ship

  Use when a user asks in ordinary language whether a change is ready, wants ShipGuard to check recent work, or requests end-to-end verification before a PR or release. Resolve and confirm scope conversationally, then orchestrate code bugs, applicable contract/invariant logic, behavior changes, visual

• sg-visual-discover

  Use when a project needs visual test manifests created or refreshed — before the first visual run, after UI routes change, or when sg-visual-run reports uncovered routes.

• sg-visual-fix

  Use when a human has annotated screenshots in the ShipGuard review dashboard and exported a fix manifest — applies the requested UI fixes and captures before/after evidence.

• sg-visual-review-stop

  Use when the ShipGuard review dashboard server should be shut down after a review session — stops the sg-visual-review HTTP server via its PID file, with a port-based fallback.

• sg-visual-review

  Use after pre-reviews, visual runs, code audits, logic audits, or process checks when results need human review — builds and serves the interactive ShipGuard dashboard.

• sg-visual-run

  Use when UI changes need visual verification — after code, logic, or process lanes flag routes, after frontend edits, or on demand to run or re-run the project's visual test manifests.

Hooks (7)

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/skills/sg-mission-lock/scripts/inject-mission-lock.mjs"

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/skills/sg-mission-lock/scripts/inject-mission-lock.mjs"

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dialogue-check.mjs"

• SubagentStart

  node "${CLAUDE_PLUGIN_ROOT}/skills/sg-mission-lock/scripts/inject-mission-lock.mjs"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dialogue-check.mjs"

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dialogue-check.mjs"

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dialogue-check.mjs"

Similar plugins