By lugassawan
Senior-engineer toolkit: principled design (Clean Arch, DDD, SOLID, TDD, patterns, observability, concurrency), security review, language expertise (Bash, C#, Dart, Go, Java, Kotlin, Python, Ruby, Rust, SQL, Swift, TypeScript), and pragmatic workflows.
Help the PR owner address review feedback — fetches open threads, presents a per-thread triage (ADDRESSED / CLARIFIED / DEFERRED), applies fixes, commits, posts per-thread replies, and resolves addressed threads.
Author an ADR, RFC, or cross-service contract via the architect subagent
Cold-start, time-boxed, multi-domain audit sweep — surfaces ranked findings with reasoning chains across security, performance, reliability, tooling, and testing
Capture an idea, improvement, or bug as a well-framed GitHub issue (works in any repo)
Clean up worktree and local + remote branch for a merged PR
Accessibility audit specialist — depth-first WCAG 2.2 AA review of frontend diffs for ARIA misuse, keyboard traps, focus mismanagement, color contrast, and screen-reader anti-patterns. Invoke when you want a focused a11y report, not a holistic code review.
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 multi-system technology selection.
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 depth-first pass.
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 invoked directly for full-feature delivery.
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.
Bash idioms — strict mode, quoting, parameter expansion, arrays, pipefail, trap cleanup, idempotency, heredocs, and POSIX portability. Auto-load when working with .sh, .bash files, or when the user mentions bash, shell, sh, shellcheck, set -e, or pipefail.
Fetch on-call and discussion context from Slack threads and PagerDuty incidents — participants, timeline, and status. Auto-loads on Slack permalinks or PagerDuty incident references. Keywords: Slack, thread, permalink, PagerDuty, incident, on-call, participants.
C# and .NET idioms — .NET 8 LTS, csproj, C# NRT, records, value semantics, switch expressions, async/await, Task, ValueTask, CancellationToken, ConfigureAwait, dependency injection, IOptions<T>, LINQ, Span<T>, ArrayPool, hot path, allocation profiling, and performance. Auto-load when working with .cs files, .csproj, .sln, Directory.Build.props, or when the user mentions C#, dotnet, .NET 8, C# NRT, NRT, records, value semantics, switch expressions, Task, ValueTask, CancellationToken, ConfigureAwait, IOptions, LINQ, Span, or hot-path code.
Dart idioms — null safety, async/await, Futures and Streams, widget composition, and Riverpod/Bloc app architecture. Auto-load when working with .dart files, pubspec.yaml, or when the user mentions Dart, Flutter, widgets, Riverpod, Bloc, Streams, or null safety.
Go idioms — error handling, concurrency, and standard library usage. Auto-load when working with .go files, go.mod, go.sum, or when the user mentions Go, Golang, goroutines, channels, interfaces, context, or error wrapping.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A senior engineer's toolkit for Claude Code — principled design, language expertise, pragmatic workflows.
swe-workbench bundles the reasoning a careful senior engineer does every day: architectural judgement (Clean Architecture, DDD, SOLID), test discipline (TDD, F.I.R.S.T.), pattern fluency (GoF and beyond), and idiomatic expertise in Bash, C#, Dart, Go, Java, Kotlin, Python, Ruby, Rust, SQL, Swift, and TypeScript. Principle and language skills auto-hint by trigger (a non-blocking hint fires when a matching file is touched); commands and subagents are there when you want explicit help.
From the marketplace:
/plugin marketplace add lugassawan/swe-workbench
/plugin install swe-workbench
For local development:
git clone https://github.com/lugassawan/swe-workbench
cd swe-workbench
/plugin marketplace add $(pwd)
/plugin install swe-workbench
/swe-workbench:review, /swe-workbench:design, /swe-workbench:architect, /swe-workbench:document, /swe-workbench:refactor, /swe-workbench:migrate, /swe-workbench:debug, /swe-workbench:implement, /swe-workbench:extend, /swe-workbench:test, /swe-workbench:security-review, /swe-workbench:capture, /swe-workbench:report-issue, /swe-workbench:cleanup-merged, /swe-workbench:sync, /swe-workbench:address-feedback, /swe-workbench:audit-codebase, /swe-workbench:codebase-knowledge, /swe-workbench:doctor — see docs/catalog.md.accessibility-auditor, architect, auditor, code-impl, conflict-resolver, contributor-auditor, debugger, dependency-auditor, e2e-test-verifier, e2e-test-writer, migrator, performance-tuner, product-designer, product-manager, redundancy-assessor, refactorer, reviewer, security-auditor, senior-engineer, tech-writer, test-reviewer, test-writer — see docs/catalog.md.ticket-context, observability-context, comms-context) — auto-load on ticket references, Sentry links, Slack/PagerDuty links to feed the full context into commands — see docs/catalog.md.development orchestrator wrapping the full 5-phase implementation lifecycle; workflow-audit-emit-issues files grouped GitHub issues from codebase audit findings.Full reference tables → docs/catalog.md. Extending guide and philosophy → docs/extending.md. Runtime dependencies → docs/dependencies.md.
Every Write and Edit tool call is scanned for hardcoded secrets (GitHub
tokens, AWS keys, .env-style assignments) before the file is written.
Detected secrets are blocked with a BLOCKED: message naming the pattern,
line number, and file. Use # nosecret on a line to suppress intentional
fixtures. See docs/secret-detection.md for the
full pattern list, suppression options, and security notes.
When Claude Code auto-compacts a long conversation, any in-progress workflow-development,
workflow-bug-triage, or workflow-pr-review state is saved to a sidecar JSON file under
.claude/cache/workflow-state/. A SessionStart hook detects this file and injects a
resume preamble so the workflow continues at the correct phase — no manual restart needed.
The hook fires on compaction as well as on plain session startup/resume, and also nudges a
worktree re-anchor when the session's cwd has drifted from a linked worktree. See
docs/workflow-state.md for the schema, lifecycle table, and a
manual smoke test.
When the orchestrator dispatches a subagent, the skills that subagent invokes are surfaced in the transcript:
Skills used by reviewer: swe-workbench:principle-code-review, swe-workbench:principle-clean-code
Top-level skill calls and zero-skill runs produce no output. Individual agents can opt out via skill_telemetry: false in their frontmatter. See docs/skill-usage-telemetry.md for full details.
See CONTRIBUTING.md.
MIT.
npx claudepluginhub lugassawan/swe-workbench --plugin swe-workbenchComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC plugin for engineering teams - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques