claude-caliper-workflow

Plugin claude-caliper-workflow from marketplace claude-caliper in nikhilsitaram/claude-caliper. Commands read from the repo's manifest — 9 days ago.

Skills (17)

• caliper-settings

  Use when the user wants to view, change, or reset their persistent preferences, or when triggered by "/caliper-settings", "my settings", "change defaults".

• codebase-review

  Use when asked to audit a codebase, find DRY/YAGNI/complexity issues repo-wide, or perform periodic code quality review

• design-review

  Use when a design doc has been written and before draft-plan is dispatched

• design

  Use when creating features, building components, adding functionality, or modifying behavior - before any creative or implementation work begins

• draft-plan

  Use when you have a spec or requirements for a multi-step task, before touching code

• handoff

  Use when the user wants to hand scoped work to a fresh, visible Claude session in a new iTerm2 pane — "/handoff", "hand this off to another session", "spin up a pane and have it do X", "open a new claude in a split and tell it to…", "delegate this to a sidecar session", "kick off a parallel session

• implement

  Use when implementing a small or medium change directly in the current session, without a multi-task plan — via design's fast-path routing, or direct invocation ("/implement", "just implement this", "quick fix").

• implementation-review

  Use when a multi-task implementation is complete and ready for holistic review before merging, or asked to review the current branch/diff as a whole

• orchestrate

  Use when executing implementation plans with independent tasks in the current session

• plan-review

  Use when a plan has been written and before execution begins

• pr-create

  Use when work is complete and ready to create a PR for review. Triggers include "/pr-create", "create a PR", "commit and push", "open a PR".

• pr-merge

  Use when a reviewed PR is ready to merge, or when triggered by "/pr-merge", "merge the PR", "merge it".

• pr-review

  Use when a PR has review feedback to address, needs review, or when triggered by "/pr-review", "address review feedback", "review feedback ready".

• queue

  Queue commands to fire automatically at a future time — by default right after the current Claude 5-hour usage window resets (so the work runs on the fresh quota in this same session), or at a time the user names. Use when the user runs `/queue <commands>`, `/queue <when> <commands>`, says "queue th

• skill-eval

  Use when evaluating skill output quality, comparing skill versions, running behavioral evals, benchmarking a skill, or when triggered by /skill-eval

• test-audit

  Use when asked to audit unit tests, check test quality/health, find flaky or weak tests, or review the test suite for smells — repo-wide or on changed tests

• usage-guard

  Work a task autonomously and continuously, checking usage-window consumption (the 5-hour block by default, or the 7-day/weekly cap with `--window 7d`) at each checkpoint, and stop when usage hits a threshold (default 99%) instead of getting rate-limited mid-action. Use when the user runs `/usage-gua

Subagents (7)

• codebase-auditor

  Read-only auditor that scans source code for DRY, YAGNI, simplicity, refactoring, and consistency issues with severity-tagged findings

• design-reviewer

  Reviews a design doc before planning begins

• implementation-reviewer

  Reviews an entire feature implementation for cross-task issues

• plan-drafter

  Writes implementation plans from design docs as a structured plan.json manifest

• plan-reviewer

  Reviews an implementation plan before execution begins

• task-implementer

  Implements a single task from an implementation plan using TDD

• test-auditor

  Read-only auditor that scans a test suite for false-pass risk, flakiness, weak assertions, poor isolation, and maintainability smells with severity-tagged findings

Hooks (3)

• PreToolUse

  bash

• SubagentStop

  bash

• PermissionRequest

  bash