claude

sdlc

Platform-agnostic SDLC orchestrator with stack-provider auto-discovery. Provides the pipeline-orchestrator skill (generic phases, review-loops, parallel groups, workflow discovery across plugins, file_glob/nested detection) plus the whole 12-agent roster (ADR-0021): BA Opus/high, developer/reviewer/tester/qa-engineer Sonnet/medium with iteration caps, security-analyst Opus/high read-only, document-writer Haiku/low, debugger read-only, devops, cicd, aar-analyst, session-recorder. Foundations supply per-role expertise (role_expertise) that is rendered into each agent's stable prefix. Commands: /sdlc:start, /sdlc:doctor, /sdlc:list-stacks, /sdlc:batch, /sdlc:security-init.

1 on GitHubby Nuclominusv3.3.0MITupdated 18 days ago
/

Plugin sdlc from marketplace agentic-sdlc in Nuclominus/agentic-sdlc-pluguin. Commands read from the repo's manifest — 15 days 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.

What it installs

Skills (6)

  • aar

    Run an After Action Review of the last SDLC pipeline run — analyze token cost and agent cooperation, then apply approved workflow improvements and persist lessons. User-triggered, never automatic. Trigger words: after action review, AAR, retrospective, review the workflow, analyze the run, post-mort

  • create-pluguin

    Scaffold a NEW SDLC plugin step by step — a framework provider (additive library) or a foundation (stack provider). Gathers identity, picks a functional aspect from the taxonomy, writes a schema-valid manifest.yaml, drafts the phase injections + a conventions skill (always asking auto vs. manual), r

  • doctor

    Diagnose SDLC pipeline health — external plugin dependencies and skill catalogs (missing per role, stale, untriaged), runtime preflight status, stale agent names or a stale config location in this project's config, and cost baseline (if available). Diagnosis is read-only; the config migration is app

  • init

    Initialize SDLC config for this project — detect the winning stack profile(s), scaffold .sdlc/sdlc.local.yaml, and optionally seed a managed block into the project's agent-instructions file. Idempotent; never overwrites existing config. Use when the user invokes /sdlc:init, or asks in natural langua

  • list-stacks

    List all stack profiles found in installed plugins, with priority and detection rules. Useful for verifying setup and debugging stack auto-detection. Use when the user invokes /sdlc:list-stacks, or asks in natural language which stack the pipeline detected, why a project matched the wrong profile, o

  • pipeline-orchestrator

    Universal SDLC pipeline orchestrator with stack provider auto-discovery. Reads manifest.yaml profiles from installed plugins, picks the highest-priority match, executes a workflow-defined pipeline (default: BA → Dev → QA → Sec → Docs). Workflows may add phases, parallel groups (e.g. [security ‖ test

Slash commands (11)

  • /sdlc:aar

    Run an After Action Review of the last SDLC pipeline run — token cost + agent cooperation, then apply approved improvements and persist lessons. User-triggered.

  • /sdlc:batch

    Run SDLC pipelines in parallel for multiple tasks — decomposes scope, detects file conflicts, dispatches worktree-isolated pipelines.

  • /sdlc:doctor

    Diagnose SDLC pipeline health — external plugin dependencies and skill catalogs, runtime preflight status, stale agent names in this project's config, and cost baseline (if available). Diagnosis is read-only; the config migration is applied only with explicit approval.

  • /sdlc:extension

    Author the Project Extension Manifest step-by-step — add per-agent Skill mappings to .sdlc/sdlc.local.yaml interactively. Validates skill/agent names; merges idempotently; never clobbers existing config.

  • /sdlc:init

    Initialize SDLC config for this project — detect the winning stack profile(s), scaffold .sdlc/sdlc.local.yaml, and optionally seed CLAUDE.md. Idempotent; never overwrites existing config.

  • /sdlc:list-stacks

    List all stack profiles found in installed plugins, with priority and detection rules. Useful for verifying setup and debugging stack auto-detection.

  • /sdlc:model-config

    Configure per-project model tiers for SDLC agents step-by-step — writes .sdlc/model.local.json. Sets a project-wide default first, then optional per-agent overrides. Validates against the registry tiers; merges idempotently; never clobbers existing config.

  • /sdlc:report

    Cross-run cost rollup across all SDLC pipeline runs — total spend, cost over time, by phase/model, cache-hit trend, cap breaches, skip frequency, QA-iteration distribution. Deterministic, no LLM tokens.

  • /sdlc:security-init

    Materialize stack-specific security-patterns.yaml and claude-security-guidance.md into the current project for the security-guidance plugin to pick up. Safe to re-run — preserves user-defined rules outside the managed block.

  • /sdlc:start

    Run the full SDLC pipeline (BA → Dev → QA → Security → Remediation? → Docs) for a feature, with auto-detection of the framework stack.

  • /sdlc:workflow-config

    Author a PROJECT-LOCAL workflow recipe step-by-step — writes .sdlc/sdlc-workflows/<name>.yaml. Prompts for phases (plain / parallel / loop), optional match rules and cost caps. Validates against schemas/workflow.schema.json; idempotent; never clobbers unrelated files.

Subagents (12)

  • aar-analyst

    Platform-neutral After Action Review analyst for the SDLC pipeline. Reads the run's _telemetry.json (via the metrics dashboard) and the session transcript, measures token cost and agent cooperation, and returns approvable workflow improvements. READ-ONLY — edits nothing; the sdlc:aar skill drives th

  • business-analyst

    Senior business analyst for ambiguous feature requests. Reads product context (Jira tickets, README, existing code) and produces user stories, acceptance criteria, data model sketches, and edge cases. <example> user invokes /sdlc:start "Add subscription billing with Stripe" orchestrator: dispatches

  • cicd

    CI/CD pipeline engineer — CI workflow definitions, lint/test/build stages, caching, matrices, artifact upload and release automation. ON-DEMAND agent (invoked directly, not by a workflow phase). Platform specifics (Gradle CI tasks, emulator jobs, signing via CI secrets, …) arrive via `resolve/cli.mj

  • debugger

    Bug investigation and root-cause analysis. Runs as the `debugging` phase of a debug/bugfix recipe AND on demand. READ-ONLY on production code: gathers evidence, reproduces, isolates, and PRESCRIBES the fix with file:line precision — the developer applies it (ADR-0018). Platform playbooks (Logcat, co

  • developer

    The implementer for the `development` and `remediation` phases on every stack. Platform-neutral process; the platform's conventions arrive as a Stack expertise block from the active foundation (ADR-0021) — invariants, rule files, and the mandatory skills to invoke. <example> orchestrator runs /sdlc:

  • devops

    Build and release engineer — build configuration, dependency/version management, build variants, signing, code shrinking/obfuscation, and store or artifact distribution. ON-DEMAND agent (invoked directly, not by a workflow phase). Platform specifics (Gradle, keystores, R8, Play Console, …) arrive vi

  • document-writer

    Final phase. Reads all prior phase outputs and creates a Pull Request with a clean description: summary, what changed, testing notes, security notes. Optionally creates a release-notes blurb for the changelog. <example> pipeline reaches phase 6/6. document-writer reads docs/plans/{slug}/01..04, call

  • qa-engineer

    Test writer and runner. Adds unit/integration/feature tests for development-phase changes. Aims for ≥80% coverage. ⚠️ HARD ITERATION CAP: Maximum 3 attempts to fix failing tests, then STOP and report. This is non-negotiable — runaway iterations are the #1 cost incident. On a recipe with a preceding

  • reviewer

    Platform-neutral code review of the development-phase changes. READ-ONLY: reports findings by severity and drives the review ⇄ development loop; never edits code (ADR-0018). The platform's review checklist arrives as a Stack expertise block (orchestrated) or via `resolve/cli.mjs expertise --role rev

  • security-analyst

    Platform-neutral security review of the development-phase changes. Applies the security standard the active stack profile supplies in its Stack expertise block (e.g. MASVS/MASTG for mobile, ADR-0021) as authoritative, with a generic baseline fallback. READ-ONLY on production code: classifies finding

  • session-recorder

    Closing phase of every SDLC run. Reads the finished run's _telemetry.json, composes a short (~20-30 word) factual note of what the run did, and appends one entry — date, slug, note, real elapsed time, cost, phase count — to the cumulative journal docs/plans/_journal.md. It is the session's closing a

  • tester

    Unit and integration test writer for the development-phase changes — the `test` phase. Writes fast, deterministic tests around the changed units (view-models/stores, repositories, mappers, services), runs them, and fixes failures within a hard cap. The platform's test stack and patterns arrive as a

Hooks (3)

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-agent-model.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-commit-guard.sh"

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/seal-run.sh"

View source on GitHub

More from Nuclominus/agentic-sdlc-pluguin

All 2 plugins →

Android Foundation — the centerpiece stack provider (Kotlin + Gradle, aspect android, priority 300, auto-detected via Gradle-AND-Kotlin). Ships NO agents (ADR-0021): the roster is the core's, and this plugin declares the Android EXPERTISE those core roles consume — role_expertise for all 11 roles (invariants, rule paths, mandatory skills) plus 20 skills: android-requirements, android-review, android-security-masvs (MASVS/MASTG), android-testing, android-e2e, android-docs-vault, android-debugging, android-build-release, android-ci, the four convention skills for Compose UI, architecture, data and Navigation, and the seven embedded framework-conventions skills (ADR-0026): retrofit, ktor, room, datastore, hilt, koin, workmanager. Frameworks are declared inline via manifest.yaml's `frameworks:` array — one row per additive library, each carrying its own `enriches_aspect` + `dependency` for conditional activation (retrofit/ktor on `network`, room/datastore-proto on `persistence`, dagger/koin on `di`, workmanager on `background` — only the detected provider per aspect activates). Plugin-resident rules, optional Obsidian vault (manage-vault skill), optional Android CLI advisory, ktlint/detekt + non-negotiable hooks. Carries pinned house rules (Coil3, Kermit, KSP, @Serializable routes, DataStore, Play Billing). Workflow android-feature: BA->Dev->Review(<->Dev x3)->[Security||Test]->QA->Docs, auto-selected on Android projects.

21 skills · hooks

1

Similar plugins

Visual workflow automation with templates, orchestration, and lifecycle management

5 skills · 8 commands · 3 agents

ruvnet/ruflo 81,589

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.

37 skills · 2 commands · hooks

anthropics/claude-plugins-official 47,076

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.

85 skills · 20 commands · 19 agents · 1 MCP server · hooks

Yeachan-Heo/oh-my-claudecode 40,800

Sales

claude

Prep calls, summarize and follow up, research accounts, review deals and pipeline, and write the forecast, using the CRM, email, calendar and chat tools your team already uses, or uploaded files. Updates records, drafts or sends email, posts to chat and books meetings when you ask.

36 skills · 23 MCP servers

anthropics/knowledge-work-plugins 35,601

Maintain sdlc?

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.

claude & codex plugins2 plugins