Development
Plugin
shep
Ship features 10x faster. Built In Auto: Memory, K8S Agent & Security (SDD+SDLC) . 😇
Plugin Signal84/100Strong
maintained100
capable70
documented100
adopted51
Install
$ npx -y skills add shep-ai/shep --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
241
Stars
51
Forks
Active
Maintenance
TypeScript
Language
MIT
License
4h ago
Last commit
6mo ago
Created
Repo: shep-ai/shep
In this plugin
- skills
- architecture-reviewer
- cross-validate-artifacts
- mermaid-diagrams
- react-flow
- shadcn-ui
- shep-kit-commit-pr
- shep-kit-fast-loop
- shep-kit-implement
- shep-kit-merged
- shep-kit-new-feature-fast
- shep-kit-new-feature
- shep-kit-parallel-task
- shep-kit-plan
- shep-kit-research
- shep-kit-status
- shep-ui-component
- tsp-model
- vercel-react-best-practices
- agents
What's inside
Skills
18/architecture-reviewerUse when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go",/cross-validate-artifactsCross-validate documentation and artifacts across the codebase for consistency, conflicts, and contradictions. Use when users ask to "cross-validate", "validate docs", "check documentation consistency", "audit documentation", or find conflicts/contradictions in docs. Supports/mermaid-diagramsComprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions,/react-flowReact Flow (@xyflow/react) for workflow visualization with custom nodes and edges. Use when building graph visualizations, creating custom workflow nodes, implementing edge labels, or controlling viewport. Triggers on ReactFlow, @xyflow/react, Handle, NodeProps, EdgeProps,/shadcn-uiProvides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind/shep-kit-commit-prUse when ready to commit, push, and create a PR with CI verification. Triggers include "commit and pr", "push pr", "create pr", "ship it", or when implementation is complete and needs CI validation. Watches CI and auto-fixes failures. Part of the Shep autonomous SDLC platform —
Show all 18 skillsShow fewer
/shep-kit-fast-loopUse when the user wants rapid implementation iteration without tests, builds, or commits. Triggers include "fast loop", "fast iteration", "just code", "no tests", "iterate quickly", or when the user says they have a dev server running and want to check results manually. Part of/shep-kit-implementValidate specs and autonomously execute implementation tasks with status tracking. Use after /shep-kit:plan when ready to start implementation. Part of the Shep autonomous SDLC platform — https://shep.bot/shep-kit-mergedUse after a PR has been merged to clean up. Switches to main, pulls latest, and deletes the local feature branch. Triggers include "merged", "pr merged", "cleanup branch", or after confirming a PR was merged. Part of the Shep autonomous SDLC platform — https://shep.bot/shep-kit-new-feature-fastFast-track feature creation that collapses new-feature, research, and planning into a single autonomous pass. Produces all spec YAMLs (spec, research, plan, tasks, feature) in one go with minimal user interaction. Triggers include "quick feature", "fast feature", "rapid spec",/shep-kit-new-featureUse when starting any new feature, functionality, or enhancement. Triggers include "new feature", "start developing", "add functionality", "implement X", or explicit /shep-kit:new-feature invocation. Creates spec branch and scaffolds specification directory. Part of the Shep/shep-kit-parallel-taskUse when a task can be worked on in isolation alongside other work. Creates a git worktree in .worktrees/ with a unique branch for parallel development. Triggers include "parallel task", "worktree", "work in isolation", or explicit /shep-kit:parallel-task invocation. Part of the/shep-kit-planUse after /shep-kit:research to create implementation plan and task breakdown. Triggers include "plan", "implementation plan", "break down tasks", "create tasks", or explicit /shep-kit:plan invocation. Part of the Shep autonomous SDLC platform — https://shep.bot/shep-kit-researchUse after /shep-kit:new-feature to analyze technical approach, evaluate libraries, document decisions. Triggers include "research", "technical analysis", "evaluate options", "which library", or explicit /shep-kit:research invocation. Part of the Shep autonomous SDLC platform —/shep-kit-statusQuick feature status and "what to do next" guide. Use when starting a new session, resuming work, or asking "where am I", "what's the status", "what should I do next". Gives a zero-to-hero walkthrough of the current feature branch. Part of the Shep autonomous SDLC platform —/shep-ui-componentUse when creating, modifying, or reviewing web UI components. Triggers include "new component", "add component", "create UI", "build a widget", "update component", working with files in src/presentation/web/components/, or when the user asks to build any React component for the/tsp-modelUse when creating, modifying, or documenting TypeSpec domain models. Triggers include adding new entities, value objects, enums, extending base types, or when asked to create a "tsp model", "domain model", "entity", or work with files in the tsp/ directory. Part of the Shep/vercel-react-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching,
Agents
10shep-clean-arch-auditorRead-only clean architecture auditor for shep. Scans a specified directory for dependency-rule violations, magic literals, singletons, oversized files, and duplication. Appends findings to a violations log in the canonical format. Use when doing a fresh sweep of a layer or ashep-cli-command-creatorScaffolds ONE new shep CLI command under src/presentation/cli/commands/, wires it to the Commander program and an existing use case via the DI container, and matches shep's exact CLI conventions (ts-node entry, injected dependencies, colored output via the shared ui module). Useshep-file-relocatorMoves ONE file from one clean-architecture layer to another (typically a pure helper from infrastructure/ → domain/shared/, or a domain error from application/use-cases/ → domain/errors/) and updates every importer in the repo. Verifies the moved file has no disallowedshep-migration-creatorCreates ONE new SQLite schema migration file under packages/core/src/infrastructure/persistence/migrations/, following shep's exact migration conventions (timestamped filename, up() function, idempotent ALTER TABLE with safe defaults). Use when shep-tsp-field-adder reported "youshep-port-creatorCreates ONE brand-new output port interface in packages/core/src/application/ports/output/ without any caller migration. Use when the caller has already designed a new boundary (e.g., ILogger, IFileSystemService, IProcessLivenessProbe) and only needs the interface file, ashep-port-extractorFixes the 'application layer imports from infrastructure' violation. Given ONE concrete infrastructure symbol (class, function, or constant) and the list of application-layer files that import it, creates a port interface in application/ports/output/, moves (or keeps) the
Show all 10 agentsShow fewer
shep-storybook-story-creatorCreates ONE Storybook story file colocated with a web UI component under src/presentation/web/components/, covering at least Default, Loading, and Error states, plus any explicit variants. Use when a component was just added and its colocated .stories.tsx is missing (mandatoryshep-tsp-field-adderAdds ONE new field (property, enum value, or base-type extension) to a TypeSpec model in tsp/, re-runs codegen, and verifies. Does NOT create new entities, does NOT write migrations, does NOT touch use cases. Use when the caller needs to extend an existing domain model (e.g.,shep-use-case-creatorScaffolds a new application-layer use case with TDD (RED test file first, then minimal GREEN implementation), wires it into the DI container, and verifies. Follows shep's mandatory patterns exactly (tsyringe decorators, port injection by string token, no infrastructure imports,shep-web-route-creatorScaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it.
Badges
4
README
1Run a fleet of coding agents. Merge real PRs.
Shep is the open-source orchestrator for the autonomous development cycle. It runs parallel AI agents — Claude Code, Cursor CLI, Gemini CLI, or any agent CLI — each in its own isolated git worktree, and drives every feature from a one-line description through optional spec gates, implementation, commit, push, CI watching with auto-fix, and a draft pull request. Agent-agnostic, local-first, MIT-licensed.
Quickstart
npx @shepai/cli # try it instantly — opens the dashboard at localhost:4050
npm i -g @shepai/cli # or install globally
Three commands from zero to an open pull request:
npm i -g @shepai/cli
cd ~/projects/my-app
shep feat new "add a /health endpoint that returns uptime and version" --push --pr
Shep creates a worktree, runs your agent, commits, pushes, and opens a PR. Requires Node.js 22+, Git, the GitHub CLI (gh), and an authenticated agent CLI (claude, cursor, or gemini). Prefer zero install? app.shep.bot runs Shep in your browser, free.
Then go parallel:
shep feat new "add stripe payments" --push --pr
shep feat new "add dark mode toggle" --push --pr
shep feat new "fix login redirect bug" --push --pr
Three agents, three worktrees, zero branch conflicts — monitored from one place. One agent session is fine; five is chaos. Shep is the part that keeps it from being chaos.
How it works
idea optional spec gates parallel agents shep automates you
"add payments" → requirements · plan → each in its own → commit · push · PR → review the diff,
(YAML you approve) git worktree CI watch + auto-fix hold the merge button
The default flow is prompt → implement → commit → push → PR. Your working directory is never touched: every feature lives in its own worktree on its own branch. If CI fails, the agent reads the logs and pushes a fix (3 retries by default, configurable). For complex features, add --no-fast to enable the full spec-driven pipeline — requirements, research, and a plan as versioned YAML artifacts, with approval gates before any code is written. See the spec-driven development guide.
Supported agents
| Agent | Support |
|---|---|
| Claude Code | Built-in |
| Cursor CLI | Built-in |
| Gemini CLI | Built-in |
| Any terminal agent CLI | Via the generic executor — if it runs in a terminal, Shep can orchestrate it |
Swap agents per feature, per repo, anytime. No lock-in at the tool layer or the model layer.
Web control center
A live graph of every repo and feature at localhost:4050 — real-time status, diff review, interactive chat, one-click open in your IDE. Everything the dashboard does, the CLI does too.
Configuration and reference
| Flag | What it does | Default |
|---|---|---|
--push | Auto-push after implementation | off |
--pr | Auto-create PR after push | off |
--fast | Skip spec-driven phases, go straight to coding | on |
--allow-merge | Auto-merge the PR after CI passes | off |
--allow-prd / --allow-plan | Auto-approve individual spec gates | off |
--allow-all | Enable all automations | off |
--model | Choose which AI model to use | agent default |
--repo | Target a specific repository | current repo |
--attach | Attach reference files for context | — |
Set defaults once with shep settings workflow so you stop repeating flags. shep settings agent, shep settings model, and shep settings ide configure the rest.
shep Start daemon + onboarding (first run)
shep feat new <description> Create a new feature
shep feat ls List features
shep feat show <id> Show feature details
shep feat resume <id> Resume a paused feature
shep feat approve <id> Approve current phase (spec-driven mode)
shep feat reject <id> --feedback Reject with feedback (spec-driven mode)
shep feat logs <id> View feature logs
shep agent ls List agent runs
shep agent stop <id> Stop a running agent immediately
shep agent logs <id> View agent logs
shep repo ls List repositories
shep start [--port] Start web daemon (default: 4050)
shep stop Stop the daemon
shep status Show daemon status and metrics
shep settings Launch setup wizard
Full reference: docs/cli/architecture.md
Shep runs entirely on your machine. All data lives in ~/.shep/ as SQLite; your code is sent only to whichever agent you configure, under that agent's own terms. Nothing is sent to Shep servers — there are none.
| Concern | How Shep handles it |
|---|---|
| Git isolation | Every feature runs in its own worktree branched from main. Your working directory is never modified. |
| Agent mistakes | Output lands as a draft PR. Your CI, linters, and security scanners run before any merge. |
| Review before merge | No code merges without your approval unless you explicitly pass --allow-merge. |
| Credentials | Shep never reads, stores, or transmits your API keys. |
| Audit trail | Every action and state transition is logged — shep feat logs <id>. |
| Emergency stop | shep agent stop <id> or the dashboard stop button. The worktree is preserved. |
Agent permissions: Shep runs your agent non-interactively, so by default it passes permission-bypass flags (e.g. --dangerously-skip-permissions for Claude Code — each agent has an equivalent). Your safety net is three layers deep: worktree isolation, draft PRs, and your CI pipeline. The bypass flag is a default, not a requirement — configure your agent's permission model independently for tighter control. Note that some agents sandbox network access by default; if npm install fails inside a feature, allow the hosts in your agent's settings.
What Shep does not protect you from: if your CI doesn't catch a vulnerability, Shep won't either. Shep is an orchestration layer, not a security scanner.
How is this different from using an AI coding agent directly? Your agent writes the code. Shep manages everything around it: worktrees, commits, pushes, PRs, CI watching, retries. The difference is most obvious at 3-5 features in parallel.
What happens if the agent writes bad code? Shep opens a draft PR and your CI runs. If tests fail, the agent reads the logs and attempts a fix (up to 3 retries, configurable), then pauses and notifies you. Shep never merges code that fails CI.
What happens when an agent gets stuck?
The feature enters a Blocked state. You get notified and can provide feedback, restart from a checkpoint, or take over — the code is a standard git worktree on a named branch, open it in your IDE at any point.
Does this work on large codebases?
Yes. The practical limit is your agent's context window, not Shep. For monorepos, scope features with --repo.
Can I use this on a team? Shep runs locally per developer. Features are just branches and PRs — your existing review process applies.
Is my code sent anywhere? Not by Shep. It goes only to the agent you configure, under that agent's privacy terms. Shep stores everything locally.
Not in a git repo yet?
Shep initializes one for you — git init, a branch, and off it goes.
Clean Architecture, four layers:
| Layer | Responsibility |
|---|---|
| Domain | Business logic, TypeSpec-generated types |
| Application | Use cases, port interfaces |
| Infrastructure | SQLite, LangGraph agents, DI |
| Presentation | CLI, Web UI |
10-minute architecture tour · Full architecture docs
Community
Shep is open source and AI-native — one of its native abilities is helping itself onboard contributors. Clone, run pnpm dev:cli doctor, pick a good first issue, and ship a PR in under 30 minutes.
- Contributing guide — humans start here (CONTRIBUTING-AGENTS.md for AI agents)
- Good first issues — groomed, scoped, ready to pick up
- Roadmap — where Shep is going
- Architecture — how the codebase fits together
- Discord — questions, feedback, show and tell
License
MIT — see LICENSE.
File tree
1795shep-ai/shepView on GitHub
.all-contributorsrc
.claude/
agents/
shep-clean-arch-auditor.md
shep-cli-command-creator.md
shep-file-relocator.md
shep-migration-creator.md
shep-port-creator.md
shep-port-extractor.md
shep-storybook-story-creator.md
shep-tsp-field-adder.md
shep-use-case-creator.md
shep-web-route-creator.md
hooks/
format-tsp.sh
rules/
cicd.md
code-quality.md
commit-conventions.md
integrity.md
operational-discipline.md
settings.json
skills/
architecture-reviewer/
SKILL.md
cross-validate-artifacts/
SKILL.md
mermaid-diagrams/
references/
advanced-features.md
architecture-diagrams.md
c4-diagrams.md
class-diagrams.md
erd-diagrams.md
flowcharts.md
sequence-diagrams.md
SKILL.md
react-flow/
references/
custom-edges.md
custom-nodes.md
events.md
viewport.md
SKILL.md
shadcn-ui/
references/
learn.md
official-ui-reference.md
reference.md
ui-reference.md
SKILL.md
shep-kit-commit-pr/
SKILL.md
shep-kit-fast-loop/
SKILL.md
shep-kit-implement/
examples/
validation-report.md
SKILL.md
validation/
architecture.md
completeness.md
consistency.md
shep-kit-merged/
SKILL.md
shep-kit-new-feature/
shep-kit-new-feature-fast/
SKILL.md
examples/
001-sample-feature/
spec.md
scripts/
init-feature.sh
SKILL.md
templates/
data-model.md
feature.yaml
plan.yaml
research.yaml
spec.yaml
tasks.yaml
shep-kit-parallel-task/
scripts/
create-worktree.sh
SKILL.md
shep-kit-plan/
examples/
sample-plan.md
SKILL.md
shep-kit-research/
examples/
sample-research.md
SKILL.md
shep-kit-status/
SKILL.md
shep-ui-component/
SKILL.md
tsp-model/
SKILL.md
vercel-react-best-practices/
AGENTS.md
rules/
advanced-event-handler-refs.md
advanced-init-once.md
advanced-use-latest.md
async-api-routes.md
async-defer-await.md
async-dependencies.md
async-parallel.md
async-suspense-boundaries.md
bundle-barrel-imports.md
bundle-conditional.md
bundle-defer-third-party.md
bundle-dynamic-imports.md
bundle-preload.md
client-event-listeners.md
client-localstorage-schema.md
client-passive-event-listeners.md
client-swr-dedup.md
js-batch-dom-css.md
js-cache-function-results.md
js-cache-property-access.md
js-cache-storage.md
js-combine-iterations.md
js-early-exit.md
js-hoist-regexp.md
js-index-maps.md
js-length-check-first.md
js-min-max-loop.md
js-set-map-lookups.md
js-tosorted-immutable.md
rendering-activity.md
rendering-animate-svg-wrapper.md
rendering-conditional-render.md
rendering-content-visibility.md
rendering-hoist-jsx.md
rendering-hydration-no-flicker.md
rendering-hydration-suppress-warning.md
rendering-svg-precision.md
rendering-usetransition-loading.md
rerender-defer-reads.md
rerender-dependencies.md
rerender-derived-state-no-effect.md
rerender-derived-state.md
rerender-functional-setstate.md
rerender-lazy-state-init.md
rerender-memo-with-default-value.md
rerender-memo.md
rerender-move-effect-to-event.md
rerender-simple-expression-in-memo.md
rerender-transitions.md
rerender-use-ref-transient-values.md
server-after-nonblocking.md
server-auth-actions.md
server-cache-lru.md
server-cache-react.md
server-dedup-props.md
server-parallel-fetching.md
server-serialization.md
SKILL.md
.cursor
.dockerignore
.editorconfig
.github/
ISSUE_TEMPLATE/
bug-report.yml
config.yml
docs-improvement.yml
feature-request.yml
good-first-issue.yml
pr-assets/
product-decisions-no-rationale.png
tech-review-product-tab-no-rationale.png
PULL_REQUEST_TEMPLATE.md
workflows/
agent-request.yml
ci.yml
claude.yml
deploy.yml
docker-publish.yml
generate-good-first-issues.yml
label-by-lane.yml
pr-check.yml
shep-e2e.yml
welcome-first-time-contributor.yml
.gitignore
.gitleaks.toml
.gitleaksignore
.husky/
commit-msg
pre-commit
prepare-commit-msg
.lintstagedrc.mjs
.nvmrc
.prettierignore
.prettierrc
.shep/
evidence/
deployment-booting-story.png
deployment-ready-no-url-story.png
deployment-ready-story.png
feature-node-unit-tests.txt
.storybook/
main.ts
mocks/
app/
actions/
add-injected-skill.ts
add-project-member.ts
add-repository.ts
adopt-agent-session.ts
adopt-branch.ts
adopt-local-directory.ts
agent-graph.ts
agent-prompts.ts
agent-questions.ts
agent-setup-flag.ts
approve-feature.ts
archive-feature.ts
aspm-ingest.ts
aspm-scan.ts
bedrock.action.ts
bulk-update-work-items.ts
check-agent-auth.ts
check-agent-tool.ts
check-all-agents-status.ts
check-tool-status.ts
compose-user-input.ts
configure-supervisor.ts
create-application.ts
create-feature-from-remote.ts
create-feature.ts
create-pm-project.ts
create-project-and-feature.ts
create-project-folder.ts
create-work-item-relation.ts
create-work-item.ts
custom-agents.ts
delete-application.ts
delete-feature.ts
delete-pm-project.ts
delete-repository.ts
delete-work-item-relation.ts
deploy-application.ts
deploy-feature.ts
deploy-repository.ts
enable-bedrock.action.ts
get-all-agent-models.ts
get-application-debug-prompt.ts
get-available-terminals.ts
get-branch-sync-status.ts
get-cycle-burndown.ts
get-default-agent-and-model.ts
get-deployment-logs.ts
get-deployment-status.ts
get-feature-artifact.ts
get-feature-drawer-data.ts
get-feature-metadata.ts
get-feature-phase-timings.ts
get-feature-plan.ts
get-git-log.ts
get-graph-data.ts
get-merge-review-data.ts
get-module-progress.ts
get-project-breakdown.ts
get-research-artifact.ts
get-supported-models.ts
get-viewer-permission.ts
get-workflow-defaults.ts
get-workflow-history.ts
github-integration.ts
global-search.ts
import-github-repository.ts
import-local-repositories.ts
list-branches.ts
list-cycles.ts
list-deployments.ts
list-github-organizations.ts
list-github-repositories.ts
list-modules.ts
list-project-relations.ts
list-sdlc-board.ts
list-work-item-relations.ts
list-work-items.ts
list-workflows.ts
load-curated-issues.ts
load-settings.ts
manage-ai-analytics.ts
manage-attachments.ts
manage-cycles.ts
manage-epics.ts
manage-import-export.ts
manage-intake.ts
manage-labels.ts
manage-modules.ts
manage-notifications.ts
manage-pages.ts
manage-project-memory.ts
manage-time-entries.ts
manage-work-item-states.ts
messaging.ts
open-directory.ts
open-folder.ts
open-ide.ts
open-shell.ts
pick-folder.ts
rebase-feature.ts
reject-feature.ts
remove-injected-skill.ts
remove-project-member.ts
reorder-sdlc-task.ts
reparent-feature.ts
resume-feature.ts
run-doctor.ts
security.ts
session-tree.ts
start-feature.ts
stop-deployment.ts
stop-feature.ts
sync-repository.ts
toggle-workflow.ts
trigger-review.ts
trigger-workflow.ts
unarchive-feature.ts
update-agent-and-model.ts
update-feature-pinned-config.ts
update-model.ts
update-pm-project.ts
update-project-member-role.ts
update-sdlc-subtask-status.ts
update-sdlc-task-status.ts
update-settings.ts
update-work-item.ts
components/
features/
chat/
ChatTab.tsx
next-image-mock.tsx
next-link-mock.tsx
next-navigation-mock.ts
preview.tsx
AGENTS.md
apis/
json-schema/
AcceptanceCriteria.yaml
ActionDispositionEntry.yaml
ActionItem.yaml
ActivityEntry.yaml
AgentAuthMethod.yaml
AgentConfig.yaml
AgentDefinition.yaml
AgentFeature.yaml
AgentGraphOverride.yaml
AgentInstance.yaml
AgentMessage.yaml
AgentMessageKind.yaml
AgentPromptOverride.yaml
AgentQuestion.yaml
AgentQuestionAnswerer.yaml
AgentQuestionKind.yaml
AgentQuestionStatus.yaml
AgentRun.yaml
AgentRunEvent.yaml
AgentRunStatus.yaml
AgentSession.yaml
AgentSessionMessage.yaml
AgentStatus.yaml
AgentType.yaml
AiChangeRiskSignal.yaml
AiSignalState.yaml
AiSignalType.yaml
AnalyzeRepoTimeouts.yaml
ApiAsset.yaml
Application.yaml
ApplicationStatus.yaml
ApplicationUpdatePayload.yaml
ApprovalGateDefaults.yaml
ApprovalGates.yaml
Artifact.yaml
ArtifactCategory.yaml
ArtifactFormat.yaml
ArtifactState.yaml
AskRequest.yaml
AskResponse.yaml
AssetType.yaml
Attachment.yaml
AuditableEntity.yaml
AuditAction.yaml
BaseEntity.yaml
BedrockHealth.yaml
BedrockLifecycleAction.yaml
BedrockMemoryFile.yaml
BedrockMemorySnapshot.yaml
BedrockTargetKind.yaml
BedrockTargetRef.yaml
BedrockTierStatus.yaml
BuildMode.yaml
BusinessUnit.yaml
CampaignStatus.yaml
CanonicalSeverity.yaml
... 1600 moreShowing a partial view of a very large repo.
FAQ
shep is a Claude Code plugin with 18 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes architecture-reviewer, cross-validate-artifacts, mermaid-diagrams. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is shep?
- Ship features 10x faster. Built In Auto: Memory, K8S Agent & Security (SDD+SDLC) . 😇
- How do I install shep?
- Run these in Claude Code: npx -y skills add shep-ai/shep --agent claude-code. Then prompt normally.
- Does shep auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is shep free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.