chrisallenlane/claude-swe-workflows
40 subagents
Subagent
doc-maintainerProject documentation maintainerqa-engineerQuality assurance engineerqa-release-engineerPre-release scanner that audits code for release readiness across multiple quality dimensionsqa-test-coverage-reviewerCoverage gap reviewer that identifies untested code paths, prioritizes by risk, and suggests refactoring for testability. Advisory only.qa-test-e2e-reviewerEnd-to-end browser test gap reviewer that detects webapps, surveys critical user journeys, and recommends gaps or starter strategies. Prescribes Playwright for greenfield. Advisory only.qa-test-fuzz-reviewerFuzz testing gap reviewer that identifies functions suitable for fuzz testing and checks for fuzz infrastructure. Advisory only.qa-test-integration-reviewerIntegration testing gap reviewer that surveys existing integration coverage, identifies trust boundaries and seams, and recommends gaps or starter strategies. Advisory only.qa-test-mutatorMutation testing worker that applies code mutations one at a time and reports which tests catch themqa-test-reviewerTest quality reviewer that identifies brittle, tautological, and harmful tests. Reports redundant tests as informational only.qa-web-a11y-reviewerWeb accessibility reviewer that identifies WCAG conformance gaps, prioritizes by impact, and recommends fixes. Advisory only.sec-blue-teamerDefensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer.…sec-red-teamerAdversarial security analyst that attacks code from the attacker's perspective to find exploitable vulnerabilitiesswe-arch-reviewerArchitecture reviewer that builds domain models and produces target blueprintsswe-bug-assessorCodebase risk assessor that cross-references complexity, coverage, structural risk factors, and git history to identify where bugs are most likely to lurk. Produces a ranked hotspot list for focused…swe-bug-hunterFocused bug investigator that deep-dives into specific code regions, writes reproducing tests for suspected bugs, and validates findings through execution. Keeps valuable tests even when they…swe-bug-investigatorBug root-cause investigator that traces failures, performs git archaeology, and produces diagnosis reportsswe-code-reviewerTactical code quality reviewer that identifies refactoring opportunities within existing architectureswe-perf-reviewerPerformance reviewer that identifies computational bottlenecks, benchmarking gaps, and optimization opportunities. Advisory only.swe-plannerSoftware implementation planning specialist that decomposes complex problems into sequential, testable sub-tasksswe-sme-ansibleAnsible automation and infrastructure-as-code subject matter expertswe-sme-cssCSS subject matter expertswe-sme-dockerDocker and containerization subject matter expertswe-sme-golangGo subject matter expertswe-sme-graphqlGraphQL API design and implementation subject matter expertswe-sme-htmlHTML subject matter expertswe-sme-javascriptJavaScript subject matter expertswe-sme-makefileMakefile optimization and best practices expertswe-sme-typescriptTypeScript subject matter expertswe-sme-zigZig subject matter expertswe-web-perf-reviewerWeb performance reviewer that identifies network, caching, loading, and asset delivery issues. Analyzes structural performance from source code. Advisory only.thk-ach-evidence-gathererGood-faith evidence enumerator for Analysis of Competing Hypotheses, parameterized by an evidence class (direct-observational, documentary-historical, structural, behavioral, absent, anomalous).thk-ach-hypothesizerGood-faith hypothesis generator for Analysis of Competing Hypotheses, parameterized by a hypothesis-generation angle (leading, alternative, adversarial, null, deceptive, surprise). Generates…thk-advocateArgues in good faith for an assigned position in adversarial proceedings. Used by /think-deliberate (arguing for one option among many) and /think-scrutinize (defending an idea against skeptics).thk-brainstormerGood-faith idea generator that produces candidate approaches for achieving a goal, parameterized by a specific brainstorming technique (first-principles, working-backwards, lateral, analogical,…thk-diagnosticianGood-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure,…thk-premortemerGood-faith failure analyst that uses prospective hindsight to identify causes of a hypothetical catastrophe, parameterized by a specific lens.thk-reflectorGood-faith reflector that extracts learnings from a completed experience, parameterized by a specific reflection lens (what-worked-vs-got-lucky, what-didn't, what-surprised, system-rewards-vs-intent,…thk-reframerGood-faith reframer that restates a problem through a specific reframing lens (problem-vs-symptom, scope-shift, stakeholder-shift, level-of-abstraction, time-horizon, inversion, category-shift,…thk-skepticGood-faith skeptic that identifies faults in an idea or plan. Spawned with a specific critical lens (technical, economic, operational, etc.) to surface fatal flaws, serious concerns, load-bearing…ux-reviewerMethodical UX advocate that reviews a draft ticket set for user-experience cogency before implementation begins. Walks a fixed seven-concern spine (coherence, completeness, mental-model fit, implicit…