Claude Code & Pi Coding Agent plugin — senior-engineer toolkit: Clean Architecture, DDD, SOLID, TDD, design patterns, security review, and language expertise across Bash, C#, Dart, Go, Java, Kotlin, Python, Ruby, Rust, SQL, Swift, and TypeScript.
Agent
Accessibility audit specialist — depth-first WCAG 2.2 AA review of frontend diffs for ARIA misuse, focus mismanagement, color contrast, and screen-reader anti-patterns. Invoke when you want a focused a11y report, not a holistic code review.
Agent
Architecture artifact author — produces ADRs, RFCs, and cross-service contracts for decisions that have no existing codebase to read. Invoke when the output must be a written decision record, not a recommendation about existing code — authoring an ADR, drafting a cross-team RFC, decomposing a service, or making a…
Agent
Cold-start codebase audit specialist — readonly multi-domain sweep across security, performance, reliability, tooling, and testing. Surfaces ranked findings with root-cause reasoning chains and counter-evidence calibration. Invoke when you want a time-boxed audit of an unfamiliar codebase, not a single-domain…
Agent
Focused implementer sub-agent — receives a scoped brief (goal, file set, verify command) from the orchestrator, implements only the assigned file group, and returns a structured summary. Invoke when swe-workbench:workflow-delegated-implementation delegates a cohesive change group to reduce orchestrator context. Never…
Agent
Conflict-resolution advisor — reads both sides of a merge/rebase conflict, reasons per-hunk, and recommends keep-mine/keep-main/manual with rationale. Invoke per conflicting file from workflow-branch-sync; never applies a resolution itself.
Agent
Contributor-trust triage specialist — depth-first review of an external PR for author signal, diff shape, repo posture, and cross-PR pattern risk. Invoke when triaging external contributions before merge, especially from first-time contributors. Advisory only — never posts to the PR.
Agent
Bug-fix specialist — root-cause via systematic-debugging, then a minimal behavior-changing fix with a regression test. Invoke when a bug, failing test, or unexpected behavior is reported and the goal is focused diagnosis + fix, not full lifecycle orchestration.
Agent
Dependency audit specialist — manifest-graph axis covering outdated versions, deprecation, license compatibility, transitive bloat, and lockfile drift across Node, Rust, Go, and Python ecosystems. Invoke when you want a focused supply-chain hygiene report, not a code-level CVE review.
Agent
E2E spec verifier — runs newly-authored specs via the project's detected E2E command, distrusts false-green passes, and confirms each spec actually exercises the stated behaviour. Invoke after e2e-test-writer; pairs with /verify or /run for async handoff.
Agent
E2E spec author — explores a live app via Playwright MCP (browsersnapshot → interact → assert), authors durable spec files, and mandates browser teardown with per-step deadlines. Invoke for the authoring phase of /swe-workbench:test --mode e2e; the verifier runs the specs after.
Agent
Migration specialist — executes schema, framework, runtime, API, and event-schema migrations through expand → backfill → switch → contract phases, each independently deployable and reversible. Invoke when transitioning code or data from version A to version B across multiple deployments — never for single-commit…
Agent
Performance triage specialist — profile-driven hotspot analysis for confirmed bottlenecks. Refuses speculative optimization requests by demanding profiling evidence first. Invoke when you have a profile (flame graph, allocation report, query log, benchmark) and need a ranked hotspot read with optimization…
Agent
UX and product design reviewer — depth-first usability heuristics, visual hierarchy, information architecture, interaction design, and design-system compliance review of frontend diffs. Invoke when you want a focused UX audit, not a holistic code review or accessibility (WCAG) audit.
Agent
Product-thinking persona that turns a rough thought (idea, improvement, bug-report) into a well-framed GitHub issue on the user's current repository. Applies four lightweight lenses — problem, value, acceptance criteria, Impact/Effort — discovers issue templates at runtime and classifies into whatever templates the…
Agent
Redundancy-assessment advisor — reads whole-file candidates the branch added against what the default branch grew independently over the same window, and recommends auto-apply/escalate/none per candidate with rationale. Invoke from workflow-branch-sync's sync --check-redundancy pass; never removes a file itself.
Agent
Refactoring specialist — applies Fowler's catalog in small, behavior-preserving steps. Invoke when cleaning up a messy function, module, or class before adding a feature.
Agent
Senior code reviewer — audits diffs for correctness, security, design, missing tests, and comment quality. Invoke when reviewing a PR, a diff, or a completed feature.
Agent
Security audit specialist — depth-first review of a diff or file for OWASP Top 10, secret leakage, insecure-by-default APIs, and language-specific foot-guns. Invoke when you want a focused security report, not a holistic code review.
Agent
Architectural advisor — thinks in boundaries, contracts, and change vectors. Invoke when choosing between approaches, scoping a new service, or evaluating an architecture.
Agent
Documentation author — generates README sections, ADRs, ARCHITECTURE/OVERVIEW, and non-obvious inline comments from diffs and conversation context, matching the repo's existing tone and conventions. Invoke when documentation is missing, stale, or drifting from code.
Agent
Test audit specialist — depth-first review of test suites for flakiness, over-mocking at internal boundaries, behaviour-vs-implementation drift, and coverage gaps. Invoke when you want a focused test audit, not authoring new tests.
Agent
Test author — writes focused, behavioural tests in language-idiomatic style. One behaviour per test, AAA, no mocks at internal boundaries. Invoke when adding tests for a function, module, or change set the user points to.
Agent
Advisory scan for unnecessary or over-cap comments, backing swe-workbench:principle-clean-code's Comment discipline caps with a deterministic, checkable artifact instead of prose recall alone. Advisory-with-accounting, not a hard gate — the scan never fails your verify step; it produces findings that verdict…
Agent
When you need to read source files from a GitHub repository other than the working repo, prefer https://gitchamber.com over fetching raw GitHub URLs or shelling out to git clone.