By Richyboy170
Self-Improving Agent: curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills. Provides /si:review, /si:promote, /si:extract, /si:status, and /si:remember slash commands.
Read-only analyst for `~/.claude/projects/<project>/memory/`. Identifies promotion candidates (entries proven enough for CLAUDE.md), stale references, consolidation opportunities, conflicts with existing CLAUDE.md rules, and reports health metrics (capacity, freshness, organization). Spawned by `/si:review`.
Transforms a proven pattern or debugging solution into a standalone, portable skill package. Generates `SKILL.md` with proper frontmatter, reference docs, and examples that work in any project (no hardcoded paths or project-specific values). Spawned by `/si:extract` when a recurring solution should become reusable.
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user runs /si:extract or asks to package a recurring solution from memory into a skill.
Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:promote or asks to make a learned behavior permanent.
Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.
Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:review or asks what has been learned and what should be promoted or pruned.
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
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.
Spec-driven, artifact-first software delivery for deep agents.
BMAD-Method Agentic SDLC is a layered software development lifecycle for agentic delivery. It uses Claude Code agents, specialist personas, BMAD skills, commands, and optional deterministic workflows to take software work from idea discovery through PRD, architecture, evaluation, story implementation, QA review, and delivery.
This repository is not primarily a website or app. Generated apps, app/, and sandbox/ are working surfaces and experiments. The core product is the agentic SDLC system.
| Layer | Role | Examples |
|---|---|---|
| Agent teams | Own lifecycle phases and specialist perspectives | cs-engineering-lead, cs-planning-lead, code-reviewer |
| Skills | Execute repeatable methods and quality gates | bmad-prd, bmad-dev-story, bmad-testarch-nfr |
| Commands | Provide user-facing entry points | /cs:workflow-build |
| Artifacts | Carry context across phase boundaries | prd.md, .decision-log.md, sprint-status.yaml |
| Workflow automation | Makes repeatable multi-agent runs deterministic | .claude/workflows/*.js |
flowchart TD
U[User goal, raw idea, or artifact paths] --> L[cs-engineering-lead]
L --> R[Phase 1: Research and discovery]
R --> P[Phase 2: PRD and requirements planning]
P --> A[Phase 3: Architecture, stories, readiness]
A --> E[Phase 4: Story implementation]
E --> Q[Phase 5: Independent QA review]
Q --> D[Final delivery digest]
R -. owns .-> RL[cs-brainstorm-research-lead]
P -. owns .-> PL[cs-planning-lead]
A -. owns .-> PL
E -. routed by .-> L
Q -. dispatched by .-> L
D --> NX[Next handoff or release decision]
The lifecycle is intentionally gated. Agents do not just chat toward code; they create artifacts, hand them off, verify them, and keep implementation tied to specs and acceptance criteria.
| Phase | Coordinator | Specialists | Primary Skills | Output Artifacts |
|---|---|---|---|---|
| 1. Research and discovery | cs-brainstorm-research-lead | cs-market-researcher, cs-tech-researcher, cs-problem-solver, cs-innovation-strategist, cs-visual-researcher, cs-concept-synthesizer, plus cs-design-thinker / cs-ideation-strategist when interactive facilitation is needed | bmad-brainstorming, bmad-market-research, bmad-domain-research, bmad-technical-research, bmad-prfaq, bmad-product-brief | Locked problem and ICP, alternatives, evidence, wedge, risks, assumptions, validation test, visual manifest when applicable |
| 2. PRD and requirements planning | cs-planning-lead | cs-concept-to-prd-planner, cs-requirements-architect, cs-prd-work-planner, cs-evaluation-architect, cs-prd-quality-reviewer, cs-epic-story-planner | bmad-prd, bmad-ux, bmad-testarch-test-design, bmad-testarch-nfr, bmad-review-edge-case-hunter | prd.md, addendum.md, .decision-log.md, FR/NFR/UJ IDs, evaluation spine, open questions |
| 3. Architecture, stories, readiness | cs-planning-lead | Planning specialists plus architecture and story workflows | bmad-create-architecture, bmad-agent-architect, bmad-create-epics-and-stories, bmad-create-story, bmad-story-automator-review, bmad-check-implementation-readiness, bmad-sprint-planning, bmad-sprint-status | Architecture artifacts, ADR/design decisions, epics, ready-for-dev stories, sprint-status.yaml, readiness verdict |
| 4. Story implementation | cs-engineering-lead | cs-frontend-engineer, cs-backend-engineer, cs-fullstack-engineer, cs-senior-engineer, cs-karpathy-reviewer | bmad-dev-story, bmad-code-review, bmad-quick-dev, bmad-testarch-atdd, bmad-testarch-trace, bmad-testarch-test-review, bmad-checkpoint-preview | Changed files, tests/checks run, implementation notes, file list, story status moved to review |
| 5. Independent QA review | cs-engineering-lead | code-reviewer, security-auditor, test-engineer, web-performance-auditor | code-review-and-quality, security-and-hardening, test-driven-development, performance-optimization, browser-testing-with-devtools | Findings by severity, coverage gaps, security risks, performance risks, approve/request-changes verdict |
Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing the pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (full API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs:workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).
End-to-end Kubernetes Operator discipline: CRD design, reconcile-loop patterns, and OperatorHub Capability Levels. Ships CRD validator, reconcile-loop linter, and capability auditor (3 stdlib Python tools), 4 references on the operator pattern + CRD design + reconcile patterns + framework comparison (controller-runtime/kubebuilder/operator-sdk/metacontroller/KOPF), CRD + Go controller skeletons, and /operator-audit slash command. NOT a generic k8s skill — specifically the Operator pattern.
Hypothesis testing, A/B experiment analysis, sample size calculation, and confidence intervals. 3 stdlib-only Python tools with Z-test, t-test, chi-square, effect sizes, power analysis, and Wilson score intervals.
End-to-end chaos engineering discipline: design experiments with hypothesis + steady-state metric + blast radius + abort criteria, calculate risk score against error budget, and generate blameless postmortems. 3 stdlib Python tools (experiment_designer, blast_radius_calculator, experiment_postmortem), 4 references on chaos principles + experiment design + 7-attack taxonomy + tooling landscape (Chaos Toolkit/Mesh/Litmus/Gremlin/AWS FIS/DIY), templates for plans + postmortems, and a /chaos-experiment slash command. Composes with feature-flags-architect (kill switches as abort triggers) and kubernetes-operator (chaos targets).
npx claudepluginhub richyboy170/agentic-sdlc-internship --plugin self-improving-agentUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns