mz-dev-pipe

Plugin mz-dev-pipe from marketplace mozg-pipelines in DoctorMozg/claude-pipelines. Commands read from the repo's manifest — 4 days ago.

Skills (5)

• ask

  Answers a question about the codebase or the web with a short sourced reply in chat. Use when the user asks "why do we use Y", "does this project support Z" or "what is the best approach to W". Not for diagram-rich code walkthroughs (use explain).

• audit

  Audits code for bugs, security and quality issues, writing a report-only findings file. Use when the user wants code checked for problems and reported without changes ("audit", "find bugs", "security review"). Not for one known bug (use debug).

• debug

  Fixes a bug test-first, or tests a hypothesis without fixing. Use when the user reports a bug, error, failing test or stack trace, or says "debug X" or "is X actually doing Y". Not for new features (use build) or getting a suite green (use polish).

• optimize

  Makes code, containers, builds or LLM hyperparameters faster, smaller or cheaper, keeping only changes a benchmark proves. Use when the user says "optimize", "make it faster" or "speed up the build". Not for tidying code (use polish).

• polish

  Removes dead code, unused imports, nesting and AI comments, behavior unchanged, or gets code past tests and CI gates. Use when the user says "clean up", "strip AI comments" or "fix failing tests". Not for one bug (use debug) or speed (use optimize).

Subagents (13)

• pipeline-code-reviewer

  Pipeline-only. Dispatched by /build, /debug, /optimize, /polish and /translate. Reviews implementation code for bugs, security issues, missed requirements, and convention violations by reading every modified file thoroughly. Do not dispatch standalone.

• pipeline-coder

  Pipeline-only. Dispatched by /build, /debug and /polish. Implements specific work units from an approved plan. Reads existing code, follows project conventions, and makes precise changes. Do not dispatch standalone.

• pipeline-completeness-checker

  Pipeline-only. Dispatched by /build. Final quality gate. Verifies the task is 100% complete by checking implementation against requirements, plan, and all review feedback. Can trigger pipeline restart from any phase. Do not dispatch standalone.

• pipeline-lint-runner

  Pipeline-only executor agent dispatched by skill orchestrators. Runs lint and/or format commands, parses per-file issues, and writes a structured lint_results.md artifact. Missing or unconfigured tools are noted but never block. Never user-triggered. When NOT to use: do not dispatch standalone, do n

• pipeline-measure-runner

  Pipeline-only executor agent dispatched by the optimize skill. Runs a measurement command with warmup and N repetitions, computes mean / median / coefficient of variation, and writes a structured measurement artifact. Never fabricates a number. Never user-triggered. When NOT to use: do not dispatch

• pipeline-optimizer

  Pipeline-only. Dispatched by /build and /polish. Cleans and optimizes code after implementation is functionally complete. Removes dead code, debug artifacts, AI residue, unused imports, duplicated logic, and unnecessary complexity without changing behavior. Do not dispatch standalone.

• pipeline-perf-candidate

  Pipeline-only implementer agent dispatched by the optimize skill. Implements exactly one performance-optimization hypothesis as one diversified candidate change in an isolated worktree, runs the correctness command, and STOPS before measuring. Never user-triggered. When NOT to use: do not dispatch s

• pipeline-plan-reviewer

  Pipeline-only. Dispatched by /build. Critically reviews implementation plans. Catches missing integration points, incorrect parallelism, incomplete test strategies, and architectural issues. Do not dispatch standalone.

• pipeline-planner

  Pipeline-only. Dispatched by /build. Creates detailed, parallelizable implementation plans. Breaks tasks into independent work units with clear file paths, changes, and dependencies. Do not dispatch standalone.

• pipeline-test-reviewer

  Pipeline-only. Dispatched by /build and /debug. Reviews tests for both coverage gaps and quality defects in a single pass. Identifies untested functions and missing code paths (Coverage section), and evaluates whether existing tests are meaningful, independent, well-structured, and would catch real

• pipeline-test-runner

  Pipeline-only executor agent dispatched by skill orchestrators. Runs the project test suite (or a subset), parses per-test results, and writes a structured test_results.md artifact. Handles scoped runs and specific test file lists. Never user-triggered. When NOT to use: do not dispatch standalone, d

• pipeline-test-writer

  Pipeline-only. Dispatched by /build, /debug and /polish. Writes comprehensive tests for implementations. Creates unit tests, edge case tests, and integration tests following project conventions. Do not dispatch standalone.

• pipeline-tooling-detector

  Pipeline-only detector agent dispatched by skill orchestrators. Reads project manifests to detect test, lint, format, and type-check tooling and writes a structured tooling.md artifact. Prefers commands named in project instructions over manifests. Never user-triggered. When NOT to use: do not dispa

Similar plugins