agentic-framework

Plugin agentic-framework from marketplace agentic-framework in dralgorhythm/claude-agentic-framework. Commands read from the repo's manifest — 1 month ago.

Skills (21)

• architect

  Design systems and record architecture decisions as ADRs — a user-invoked Principal Architect workflow.

• designing-systems

  Produces this framework's ADR and system-design artifacts from bundled templates with trade-off analysis. Use when designing a system or component, choosing between architectures, or recording an architecture decision in the planning flow.

• writing-adrs

  Document architectural decisions. Use when making significant technical decisions that should be recorded. Covers ADR format and decision documentation.

• builder

  Translate plans into working, tested code through implementation, debugging, and refactoring — a user-invoked Builder workflow.

• code-check

  Audit a codebase holistically for SOLID, DRY, and consistency violations — a user-invoked Codebase Auditor workflow.

• dependency-upgrade

  Sequences safe dependency upgrades — verified pins, staged rollout, changelog gates. Use when upgrading or bumping a dependency, reviewing a Dependabot or Renovate PR, resolving a lockfile conflict, applying a CVE-driven update, or pinning a GitHub Action or git tag.

• review-steering

  Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives. Use when creating or updating REVIEW.md, configuring or steering automated code review, or reconciling r

• testing

  Write effective tests for code quality and reliability. Use when implementing features, fixing bugs, improving coverage, or practicing TDD/test-driven development. Covers unit, integration, and E2E testing.

• land-the-plane

  Lands in-flight work: quality gates, atomic commit, rebase, push, verified remote sync, then handoff — a user-invoked finish-line workflow.

• postmortem

  Runs this framework's blameless postmortem workflow — reconstruct the incident timeline from evidence, drive five-whys to a mechanism-level root cause, and produce owner-and-due-date action items with a regression guard. Use when an incident just resolved, running an outage retrospective, writing a

• swarm-coordination

  Coordinate multi-agent swarm workflows. Use when working in parallel with other agents, managing shared resources, or orchestrating distributed tasks. Covers conflict prevention, handoffs, and two-tier task tracking (native task list + artifacts).

• planning-artifacts

  Produces this framework's planning artifacts — PR-FAQ (working-backwards vision), PRD (requirements), and execution roadmap — from their bundled templates. Use when writing or updating a PR-FAQ, PRD, product requirements, or delivery roadmap, or when the planning flow calls for one.

• qa-engineer

  Define test strategy and verify quality against WCAG and testing-pyramid criteria — a user-invoked QA Engineer workflow.

• security-auditor

  Assess vulnerabilities and audit for security compliance using OWASP and STRIDE methodology — a user-invoked Security Auditor workflow.

• threat-modeling

  Identify and analyze security threats. Use when designing a feature with security implications, before implementing auth/input-handling code, or when an audit calls for a threat model. Covers STRIDE methodology.

• swarm-execute

  Execute an implementation plan with parallel worker swarms, quality gates, and native task tracking — a user-invoked Execution Orchestrator workflow.

• swarm-plan

  Decompose a feature into an actionable implementation plan using parallel worker-explorer swarms — a user-invoked Planning Orchestrator workflow.

• swarm-research

  Coordinate parallel research workers to investigate a topic deeply and synthesize citation-backed findings — a user-invoked Research Orchestrator workflow.

• swarm-review

  Run an adversarial, multi-perspective code review with root-cause analysis and security focus — a user-invoked Adversarial Reviewer workflow.

• tailor

  Detects the project's stack from manifests and proposes tailored framework configuration — filled tech-strategy golden paths, REVIEW.md/CLAUDE.md review steering, and a prune list of unused framework pieces — as a reviewable plan, never silent writes.

• ui-ux-designer

  Design interfaces and validate accessibility against WCAG 2.1 with DevTools-backed checks — a user-invoked UI/UX Designer workflow.

MCP servers (4)

• sequential-thinking

  runs: npx -y @modelcontextprotocol/server-sequential-thinking

• chrome-devtools

  runs: npx -y chrome-devtools-mcp

• filesystem

  runs: npx -y @modelcontextprotocol/server-filesystem .

• context7

  runs: npx -y @upstash/context7-mcp

Hooks (10)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/session-start-loader.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/pre-tool-use-validator.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/dangerous-command-guard.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/pre-commit-verification.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/pre-push-main-blocker.sh"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/branch-pr-discipline.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/post-tool-use-tracker.sh"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/post-edit-lint.sh"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/stop-validator.sh"

• SubagentStop

  "${CLAUDE_PLUGIN_ROOT}/.claude/hooks/subagent-stop-validator.sh"

Similar plugins