Plan creation, review, follow-through, and maintenance. Author an interactive HTML plan (implementation-plan), implement it through the acceptance and completion gates (build), review it (review-plan, finalize-plan), and ship a backlog in parallel (build-fleet). Also ships build-proposal, build-feature, deep-grill, prompt, prototype, design, publish-hub, documenting-plans, markdown-to-html, plan-status, plans-library, plans-open, and setup-sites. Full detail in the plugin README.
Plugin plan-agent from marketplace agentics-kit in shawn-sandy/agentics. Commands read from the repo's manifest — 6 days ago.
build-featureTurns a feature idea into a product feature doc for the team. Adds stories, acceptance criteria, metrics, rollout, and a sized sub-feature breakdown. Use when scoping a feature to build.
build-fleetShips a backlog of plans in parallel, one isolated worktree agent per plan. Each agent builds its plan, opens a PR, and watches CI. Use when asked to implement a plan backlog in parallel.
build-proposalTurns a vague idea into a decision-complete proposal. Researches web and codebase, separating established facts from open decisions. Use when the user floats an idea or asks should-we.
deep-grillStress-tests plan decisions node-by-node with focused questions. Walks each decision point surfacing assumptions and weak spots. Use when the user asks to deep grill or stress-test a plan.
designGenerates a design canvas from a plan. Derives one artboard per user-facing step and links the published canvas back into the plan spec. Use when asked to design or mock up a plan.
documenting-plansGenerates a prose reference doc from a completed plan. Inspects the codebase and git history to produce accurate, evidence-backed documentation. Use when the user asks to document a completed plan.
finalize-planMarks a plan as completed. Verifies codebase evidence, ticks acceptance criteria, and re-renders the HTML; --all sweeps unmarked plans. Use via /plan-agent:finalize-plan.
implementation-planGenerates HTML implementation-plan documents. Produces a self-contained .html plan file with steps, acceptance criteria, and metadata. Use when the user asks to create or generate an HTML plan file.
markdown-to-htmlConverts a markdown file into a self-contained HTML page. Produces styled output with syntax highlighting and responsive layout. Use when the user asks to convert a markdown file or plan to HTML.
plan-statusWrites lifecycle status into a plan's frontmatter, one file or a directory. Inspects codebase and git history for accurate dates. Use when asked to check or update plan status.
plans-libraryBuilds and opens a filterable HTML gallery of all plans in the plans directory. Scans HTML plans, parses metadata, and writes index.html. Use when asked to browse plans or view plan history.
plans-openOpens the existing plans gallery without rebuilding. Opens index.html directly; run plans-library first if not yet built. Use when asked to reopen the plans gallery or browse plans without a rebuild.
promptBuilds structured AI prompts using Anthropic techniques. Interviews users, classifies prompt type, and delivers a copy-pasteable prompt. Use when the user asks to write, refine, or build a prompt.
prototypeGenerates a runnable static-HTML prototype from a plan, idea, or design. Produces one self-contained, framework-free clickable file under docs/prototypes/. Use when asked to prototype a mockup.
publish-hubBundles a plan and its related HTML into one tabbed hub artifact. Publishes plan, prototype, and extras to one stable claude.ai URL. Use when asked to publish or share a plan hub.
review-planPlan review reviewer panel. Reviews implementation plans in parallel, refutes weak findings, and applies improvements in place. Use when the user asks to review or improve an implementation plan.
setup-sitesScaffolds GitHub Pages publishing into any repo. Adds the deploy workflow, .nojekyll, hub, and preview script so docs/ HTML reaches a public URL. Use when asked to set up or publish GitHub Pages.
/plan-agent:deep-grillWalk each decision branch in an implementation plan with focused questions and codebase exploration
/plan-agent:documenting-plansGenerate developer-friendly documentation at docs/<slug>.md from a completed plan file, synthesized from the plan body, live code inspection, and git history
/plan-agent:fixAuthor and implement a fix plan — the /plan-agent:build chain, typed as a fix
/plan-agent:markdown-to-htmlConvert a markdown file or plan to a rich, self-contained HTML document viewable in any browser
/plan-agent:plan-maintenanceArchive completed plans as HTML, generate a README index, and review variant/duplicate files
/plan-agent:plan-statusCheck and update the lifecycle status of a plan file (todo, in-progress, completed) with type classification (feature, fix, refactor, docs, chore)
/plan-agent:promptBuild a structured AI prompt using Anthropic techniques and save it to the prompts directory
/plan-agent:refactorAuthor and implement a refactor plan — the /plan-agent:build chain, typed as a refactor
/plan-agent:review-plan-bgRun the plan-agent review team in the background. Pass the plan path as argument.
agent-review-planBackground plan-review agent. Runs the ten-reviewer Workflow (architecture, completeness, testability, risk, conventions, product, security + conditional UX, accessibility, and frontend) on an implementation plan without blocking the parent session. Improves and updates the plan in place. Use when d
plan-documenterBatch documentation agent that scans the plans directory for completed plans without corresponding documentation in docs/, then invokes the documenting-plans skill for each one. Use when delegating bulk plan documentation, running a scheduled weekly documentation sweep, or generating docs for all co
plan-reviewer-accessibilityReviews UI implementation plans for WCAG 2.1 AA compliance, semantic HTML, keyboard navigation, and screen reader support. Use only for plans that touch React, Vue, UI components, or user-facing flows.
plan-reviewer-architectureReviews implementation plans for architectural soundness, design pattern fit, and system integration coherence.
plan-reviewer-completenessReviews implementation plans for completeness — ensuring no steps are vague, no critical files are omitted, and the path from plan to done is unbroken.
plan-reviewer-conventionsReviews implementation plans for adherence to project conventions, code style, naming patterns, and organizational consistency.
plan-reviewer-frontendReviews UI implementation plans for frontend engineering — component boundaries, state placement, render cost, and design-system alignment. Use only for plans that touch React, Vue, UI components, or user-facing flows.
plan-reviewer-productReviews implementation plans for product value — user problem, scope sizing, success metrics, load-bearing assumptions, and rollout readiness.
plan-reviewer-riskReviews implementation plans for risks and failure modes — identifying breaking changes, data loss, concurrency issues, and dependency hazards.
plan-reviewer-securityReviews implementation plans for security posture — authn/authz, data handling, input validation at trust boundaries, secrets, and dependency risk.
plan-reviewer-testabilityReviews implementation plans for testability — ensuring changes are covered by real application tests and acceptance criteria are verifiable.
plan-reviewer-uxReviews UI implementation plans for user experience fitness, interaction design clarity, and flow coherence. Use only for plans that touch React, Vue, UI components, or user-facing flows.
Automated git workflow — create branches, commit with conventional messages, create PRs, and open GitHub/GitLab issues from any context (selection, session, bug, feature) with host auto-detection and confirmation gate; ships background subagents and slash commands for fire-and-forget commit/PR/ship/CI-watch plus auto-linking plan issue references in PR descriptions
8 skills · 5 commands · 5 agents
Discover teachable code, blog posts, videos, GitHub snippets, and selected/pasted code — scrub for secrets, draft instructional platform-aware copy with concrete takeaways, and generate styled dark-mode social cards for LinkedIn, Twitter/X, Bluesky, and Substack, plus a write-guide skill that writes long-form internal developer explainer guides to docs/
17 skills · 1 command
Publish diffs, sessions, plans, prompts, and teaching pages as live claude.ai artifact pages — an annotated diff walkthrough with per-hunk reviewer notes, a reviewer-first session recap, plan HTML republished to a stable URL, a filterable prompt library with verbatim copy buttons, and a teach-artifact explainer — plus product-doc, team-recap, and eng-recap audience framings over the session recap, with a blocking secret-scrub gate and a local-HTML fallback.
5 skills · 3 commands
Analyze code and suggest specific, purpose-driven tests tied to actual behavior and intent — not arbitrary coverage
6 skills
Review and optimize Claude Code skill files — score SKILL.md quality, plan and scaffold new skills, audit allowed-tools permissions, optimize frontmatter (descriptions + disable-model-invocation), and enforce the three-part 200-char description format
4 skills · 1 command
Structured multi-dimensional code review across quality, bugs, security, best practices, complexity rating, breaking changes, and regressions
1 skill · 1 command · 1 agent
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
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
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.