claude

shepherd

Shepherd: SDLC orchestration + one-command install of the full delivery harness (governance CLAUDE.md, CI rail gates + eval workflows, Stop/review hooks, build-loop agents & skills, IaC starters) — GitHub or Azure DevOps, with the optional Shepherd desktop app.

9 on GitHubby Matt Kruczekv2.1.0MITupdated 27 days agosdlc
/

Plugin shepherd from marketplace mckruz in MCKRUZ/shepherd-sdlc. Commands read from the repo's manifest — 27 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 (10)

  • shepherd

    SDLC orchestration plugin for Claude Code. Drives projects through a 9-phase software development lifecycle with company-configurable profiles, compliance gates, and quality enforcement. Triggers: "start sdlc", "sdlc setup", "initialize project lifecycle", "run phase gate", "advance phase", "sdlc st

  • api-pattern-dotnet

    Add a new endpoint / MediatR command or query / handler / service the way this .NET codebase already does it. Use when building an API surface, a CQRS handler, a controller, a validator, or a DI registration in a .NET / Clean Architecture repo. Finds the one canonical example and mirrors its layerin

  • api-pattern-node

    Add a new endpoint / route / use case / service the way this Node + TypeScript codebase already does it. Use when building an API surface, a request handler, a validator, a port/adapter, or a container registration in a Node/TypeScript repo. Finds the one canonical example and mirrors its layering,

  • api-pattern-python

    Add a new module / CLI command / service function / loader the way this Python codebase already does it. Use when building a public surface, a command entry point, a data loader, a validator, or a new package module in a Python / uv repo. Finds the one canonical example and mirrors its layering, typ

  • api-pattern

    Add a new endpoint / handler / service the way this codebase already does it. Use when building an API surface, a CQRS handler, a controller, or a service registration. Finds the one canonical example and follows it exactly — so agents reuse the established pattern instead of inventing a new one eac

  • diagnose

    The team's bug-fix procedure: reproduce with a FAILING TEST first, then fix, then prove the test passes. Use whenever a bug is reported. Do not start by patching — start by reproducing. For deep root-cause hunts, invoke the debugger agent from inside this procedure.

  • eval-builder

    Build a golden set for an agentic (LLM-powered) spec — the acceptance criteria for probabilistic behavior. Use when a spec's deliverable is an agent/prompt/tool and needs evals before build, or when adding cases from a production failure. Produces a versioned golden-set.yaml under eval-datasets/spec

  • pr-writer

    Open a spec's PR correctly: the right branch, a conventional-commit title, a body that maps the diff to the spec's acceptance checks with a test plan, and the spec file included in the diff. Use when a change is ready to push for review.

  • spec-writer

    Turn a backlog story into a Definition-of-Ready spec at specs/NNNN-name.md. Use when the user wants to "write a spec", "make this story ready", or start a feature. Enforces the vague-line test on every acceptance check and assigns a risk tier. Use BEFORE delegating any build — no spec, no build.

  • test-writer

    Write tests that encode WHY behavior matters, mapped to a spec's acceptance checks. Use when adding tests for a feature or reproducing a bug. For bug fixes, write the failing test FIRST. Targets the team's coverage bar on new code.

Slash commands (33)

  • /shepherd:sprd-ado
  • /shepherd:sprd-audit-artifacts
  • /shepherd:sprd-audit
  • /shepherd:sprd-brief
  • /shepherd:sprd-channel
  • /shepherd:sprd-coach
  • /shepherd:sprd-data
  • /shepherd:sprd-doctor
  • /shepherd:sprd-enhance
  • /shepherd:sprd-evals
  • /shepherd:sprd-experience
  • /shepherd:sprd-feature
  • /shepherd:sprd-gate
  • /shepherd:sprd-handoff
  • /shepherd:sprd-harness
  • /shepherd:sprd-intake
  • /shepherd:sprd-next
  • /shepherd:sprd-phase-report
  • /shepherd:sprd-refine
  • /shepherd:sprd-refresh
  • /shepherd:sprd-retro
  • /shepherd:sprd-review
  • /shepherd:sprd-revise
  • /shepherd:sprd-rules
  • /shepherd:sprd-setup
  • /shepherd:sprd-spec-status
  • /shepherd:sprd-spec
  • /shepherd:sprd-spike
  • /shepherd:sprd-sprint
  • /shepherd:sprd-status
  • /shepherd:sprd-upgrade
  • /shepherd:sprd-version
  • /shepherd:sprd

Subagents (14)

  • bizreq-analyst

    Business-requirements agent — authors business-rules.md (a BR-NN decision table) and golden-scenarios.md (SCEN-NN), the domain logic and worked examples that pin down "correct" before anyone builds. Runs standalone, as the driver of /sprd-rules (Phase 1), and composed by /sprd-evals and the /sprd-re

  • compliance-checker

    Validates compliance gates at SDLC phase transitions for SOC 2, HIPAA, GDPR, and PCI-DSS

  • conversation-designer

    Design-discipline agent for conversational surfaces (the voice and chat channels) — authors the user journey, surface layout (turn-script or message-flow), and the voice/chat interaction contract. Runs standalone, as the /sprd-experience designer for voice/chat, or as the /sprd-review Design lens (P

  • data-analyst

    Data-discipline agent — authors the PII-classified data-contract, the data-readiness assessment (advisory), and the lineage-audit for a feature or spec and, for a data spec, the data dictionary, decision memo and handoff. PII is a risk-tier driver; readiness gaps become decision-log items. Runs stan

  • discovery-analyst

    Cross-document analysis for discovery — finds contradictions across an intake corpus and generates the pre-workshop question list. Runs standalone or as Phase 0 Step 0d.

  • document-summarizer

    Writes the per-document summary for one document in the intake corpus, to the document-summary template and token budget. Runs as Phase 0 Step 0c, once per document, standalone or in a project.

  • feature-architect

    Product-discipline agent for the featuring hop — decomposes one epic into channel-aware features and specs, drafts feature-brief.md, proposes the decomposition and risk tiers, and opens decision-log items. Runs standalone or as the driver of /sprd-feature (Phase 1).

  • gate-repair

    Attempts to fix simple gate failures (missing templates, incomplete sections, placeholder content) before escalating to human

  • multi-reviewer

    Multi-perspective review agent with adversarial, edge-case, and council modes for challenging phase artifacts

  • narrative-enhancer

    Transforms technical SDLC artifacts into prose-rich stakeholder-friendly companion documents

  • requirements-analyst

    Guides discovery interviews and decomposes problems into structured requirements with acceptance criteria

  • sdlc-orchestrator

    SDLC phase coordinator that manages phase transitions, skill invocation, and lifecycle orchestration

  • section-evaluator

    Evaluates completed section implementations against their section plan's Verification Criteria and Evaluator Contract

  • visual-designer

    Design-discipline agent for web/visual surfaces (the ag-ui channel) — authors the user journey, surface layout (screens), and the channel-interaction-spec that is the AG-UI event contract. Runs standalone, as the /sprd-experience designer for ag-ui, or as the /sprd-review Design lens (Phase 2).

Hooks (1)

  • SessionStart

    pwsh -NoProfile -ExecutionPolicy Bypass -File "${CLAUDE_PLUGIN_ROOT}/hooks/shepherd-session-start.ps1" || bash "${CLAUDE_PLUGIN_ROOT}/hooks/shepherd-session-start.sh"

View source on GitHub

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

1 command · 6 agents

anthropics/claude-code 155,476

Taste Skill

claudecodex

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

Leonxlnx/taste-skill 114,391

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

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

Maintain shepherd?

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 pluginslisted