flywheel
claudecodexGuide software project work from shaping and execution through review, branch finishing, and reusable repo knowledge.
32 skills · hooks
Guide software project work from shaping and execution through review, branch finishing, and reusable repo knowledge.
Plugin fw in mopeyjellyfish/flywheel. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
architecture-strategyAssess repo-grounded architecture choices and improvements. Use for boundaries, service splits, dependency direction, or distributed posture.
brainstormExplore requirements and approaches. Use for a fuzzy idea, open scope, or one direction that needs sharper behavior before planning.
browser-testRun browser acceptance checks with playwright-cli. Use when browser-visible behavior needs fresh proof before review or commit.
commit-messageDraft Conventional Commit messages. Use when choosing a commit header, body, footer, or breaking-change marker.
commitFinish a branch cleanly. Use to verify readiness, make logical commits, push, and create or refresh a PR with evidence.
debugInvestigate hard bugs, regressions, stack traces, or broken behavior with evidence, a repro loop, causal proof, and a fix path.
decisionGrill and capture durable decisions. Use for ADRs, terminology conflicts, tradeoffs, or spec decision review.
deepenGrill and strengthen an existing plan. Use to align source docs, decisions, vertical slices, tests, and rollout before work.
docsWrite or refresh Diataxis project docs. Use when setup, APIs, CLI flows, config, workflows, or behavior changed.
document-reviewReview requirements or plan docs. Use to surface severity, confidence, and a ranked fix queue before planning or work.
ideateGenerate and filter grounded next bets. Use when the work is not chosen and the user wants ranked ideas before brainstorming.
incidentHandle runtime incidents from live evidence. Use to bound blast radius and choose mitigation, rollback, or patch.
loggingDesign or review structured logging. Use when runtime behavior needs useful events, stable fields, or correlation IDs.
maintainabilityAssess future edit cost. Use when wrappers, helpers, naming, cohesion, or ownership may make changes harder.
observabilityDesign or review runtime observability. Use for logs, metrics, traces, dashboards, validation, and supportability.
optimizeRun measured optimization loops. Use for latency, throughput, resource, cost, build, or query improvements that need proof.
pattern-recognitionAssess pattern fit from repo truth. Use when deciding whether DTOs, repositories, ports, builders, DDD, or similar patterns fit.
planCreate read-only implementation plans. Use for requirements, bug reports, feature ideas, or rough tasks before execution.
polishRun an interactive browser polish loop. Use to tighten browser-visible work with live feedback before review or commit.
researchResearch a topic with repo and current-source evidence. Use when findings should sharpen shaping, review, or planning.
reviewRun structured code review. Use before PRs or merges to find bugs, regressions, missing tests, and readiness gaps.
rolloutPlan release posture for runtime-risky changes. Use for validation, sequencing, rollout, rollback, and blast radius.
runOptionally orchestrate remaining Flywheel stages. Use only when one coordinated pass is better than manual stage handoffs.
setupDiagnose and bootstrap repo-local setup. Use for onboarding, workflow readiness, host posture, or missing tool checks.
shapeShape work before implementation. Use to choose ideation, brainstorming, planning, or plan-deepening before work.
simplifyReduce accidental complexity in recent code. Use when wrappers, abstractions, or orchestration no longer earn their keep.
spinCapture durable lessons in docs/solutions. Use after completed work, verified fixes, or repeated repo-specific patterns.
startRoute project work through Flywheel. Use to pick the earliest useful stage from shape, work, review, spin, or commit.
tddEnforce red-green-refactor for feature work, bug fixes, refactors, and behavior changes.
verifyVerify completion claims with fresh evidence. Use before claiming tests, lint, builds, fixes, or requirements are done.
workExecute ready implementation work. Use for plans, specs, todos, or clear requests that need tracked changes and validation.
worktreeManage isolated git worktrees. Use for branch work, isolated review targets, parallel checkouts, or cleanup.
node "${CLAUDE_PLUGIN_ROOT}/hooks/flywheel-hook-policy.js" pre-tool claude
node "${CLAUDE_PLUGIN_ROOT}/hooks/flywheel-hook-policy.js" stop claude
Guide software project work from shaping and execution through review, branch finishing, and reusable repo knowledge.
32 skills · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.