core

Plugin core from marketplace swarmery in atretyak1985/swarmery. Commands read from the repo's manifest — 9 days ago.

Skills (37)

• api-contract

  Verify field-level alignment between ORM schema, Zod schemas, and route handler shapes, or that SQL migrations match ORM tables. NOT for writing new routes (use api-integration) or code style (use code-standards).

• api-integration

  Implement REST route handlers, ORM queries, WebSocket telemetry, or SSE endpoints in the main web app, or consume those APIs from clients. NOT for schema-only changes or deployment/infra config.

• area-lessons

  Use this skill when the operator wants to see the active lessons learned by earlier headless runs for the directory they are working in, pulled on demand from the local swarmery daemon. Read-only. Don't use it to accept, edit or promote lessons (that is the daemon's Lessons page) or to search code (

• automation

  Convert an operational runbook (pod restarts, cache flushes, scaling) into a parameterized idempotent script with safety gates, or design a chaos experiment. NOT for CI/CD or deployment manifests (use deployment).

• browser-verification

  Verify UI behavior in a live browser via Playwright MCP (navigate, snapshot, screenshots, console/network) against localdev or staging. NOT for full domain E2E flows and never against production.

• c4-architecture-docs

  Document an epic/feature architecture with the C4 model -- system context/container/component/dynamic diagrams as Mermaid .mmd plus a narrative doc. NOT for rendering an existing .mmd (use mermaid-viewer).

• code-quality

  QUANTITATIVE structural metrics on TS/Python -- function length, cyclomatic complexity, nesting, duplication, code smells -- scored report. NOT for conventions/`any` checks (use code-standards) or API alignment (use api-contract).

• code-search

  Select the right search tool (Grep, Glob, codebase-retrieval) to locate existing code, symbols, or files across the project's monorepo. Don't use it for creating new files, implementing features, or reviewing code quality.

• code-standards

  Review code against CONVENTIONS -- type safety (`any` detection), naming, imports, Next.js patterns, 12-factor. NOT for complexity metrics (use code-quality) or API field alignment (use api-contract).

• context-optimization

  Use this skill when a task spans 3+ files or crosses repo boundaries and context usage must be managed. Don't use it for single-file edits or read-only queries.

• deps-check

  Use this skill when auditing dependency versions, checking for outdated packages, or scanning for security vulnerabilities across the project's repos. Don't use it for upgrading packages (that requires a separate implementation task) or for deployment config template issues (use deployment).

• docker-build

  Use this skill when building or pushing Docker images for the project's services (the main app, the device service) to the cloud container registry. Don't use it for deploys (use deployment) or Dockerfile template editing without a build (use code-quality).

• env-check

  Use this skill when a task involves adding, removing, or renaming environment variables across the project's repos OR verifying env var documentation before a release. Don't use it for runtime env introspection in a live cluster (that requires exec access to the running service).

• founder-reality-check

  Use this skill when the user asks for an investor-mode reality check on the product/business — audit the shipped state against the business thesis with VC-style critique. Don't use it for code review or feature planning.

• functional-design

  EXECUTES refactors of TypeScript business logic toward pure functions, immutability, and pipelines -- edits files via Edit. NOT for planning-only refactors (use refactor-plan) or I/O-heavy handlers / Python paths.

• git-commit

  Generate conventional commit messages when staging files for commit in any of the project's repos. Do not use for git tag messages, merge commit messages, changelog entries, or automated version bump commits.

• guardrails

  Use this skill before executing a risky or hard-to-reverse action — migrations, deletions, deploy/config changes, force operations — to derive a risk level and an APPROVED/REJECTED call with a rollback plan. Don't use it for routine read-only work.

• html-reporting

  Render a self-contained HTML report or dashboard (task summaries, code/operational audits) in one canonical dark-terminal shell. NOT for markdown-only output or the mermaid viewer (use mermaid-viewer).

• jira-tasks

  Read-only Jira for the project's tracker: my tickets, open tickets, ticket status, jira backlog, link a workspace task to a ticket. NOT for write ops (create/transition/comment/log-work) and NOT for Confluence.

• mermaid-viewer

  Use this skill when the user has a Mermaid source file (.mmd) and wants to view it in a browser -- asking to convert mermaid to html, render this diagram, make an HTML viewer, or make the schema explorable. Don't use it for generating new diagrams from scratch or exporting to PNG/PDF.

• migration-check

  Validate SQL migration safety, ORM-to-migration alignment, or schema drift between the DB and Zod/DTO types. NOT for deployment config (use deployment) or IaC drift (use infrastructure-as-code).

• monitoring

  Prometheus metrics, Grafana dashboards, alert rules, ServiceMonitor wiring, and endpoint instrumentation. NOT for logs/traces (belong to observability) and NOT for Helm health probes.

• monorepo-coordination

  Coordinate changes spanning 2+ repos of a multi-repo workspace or 2+ apps/packages of a monorepo -- merge-order plans, MR/PR templates, post-merge checklists. NOT for single-repo changes, even large ones.

• observability

  Structured logging and OpenTelemetry distributed tracing, incl. log-trace-metric correlation. NOT for metrics/dashboards/alerts (belong to monitoring) and NOT for Helm health probes.

• pr-generator

  Use this skill when creating a pull request — generate the title, structured description, and review checklist from the branch's actual commits and diff. Don't use it for commit messages (git-commit skill) or changelogs.

• refactor-plan

  PRODUCES a refactoring plan ONLY -- impact analysis, step ordering, risk, rollback -- NO code changes. NOT for executing refactors (use functional-design) or dependency upgrades (use deps-check).

• run-plan

  EXECUTES an existing @planner plan -- parses the phase DAG, dispatches per-phase implement+review loops, preserving ASK gates. NOT for creating plans; NOT usable from inside a subagent.

• security-audit

  Scan application code for security vulnerabilities, OWASP Top 10 compliance, or hardcoded secrets across the project's repos. NOT for CI/CD hardening or SBOM generation (use supply-chain-security).

• session-closeout

  Use this skill when closing a finished task — writing the SUMMARY.md final report, the phase-09 retrospective, and task documentation in the workspace task dir. Don't use it for mid-task status updates or commit messages.

• sprint-review

  Use this skill for an end-of-sprint read-only audit — scope recent changes across repos, fan out review agents, run check-only suites, and produce a PASS/FAIL report. Don't use it for reviewing a single PR or diff.

• sre-operations

  Use this skill for SRE work — SLO definition, incident response, capacity planning, toil reduction — with human gates on every destructive operation. Don't use it for application debugging (troubleshooting skill) or metrics wiring (monitoring skill).

• summary-templates

  Use this skill when a task involves summarizing completed work, writing a feature summary, documenting what changed, or creating a completion report for a task, feature, bug fix, or refactoring. Don't use it for writing documentation, changelogs, or postmortems.

• supply-chain-security

  Audit and harden container supply-chain controls: image scanning, SBOM generation, immutable digest promotion, rollback retention, and image signing readiness. Not for application code vulnerabilities (use security-audit) or pipeline YAML structure (use deployment).

• test-coverage

  FIND test coverage gaps (read-only) -- map source to test files, flag untested modules by risk. NOT for writing/running/debugging tests (use testing) or measuring coverage percentages (run --coverage directly).

• testing

  WRITE, RUN, or DEBUG tests -- pytest, Jest/RTL, Playwright E2E, deployment config. NOT for finding coverage gaps (use test-coverage) or CI pipeline config (use deployment).

• troubleshooting

  Debug a specific failure, investigate an incident, analyze error logs, or diagnose connectivity on the project's platform. NOT for proactive instrumentation (use monitoring/observability) or writing tests (use testing).

• workspace-plans

  Use this skill when writing, revising, or executing a workspace plan — the plan/README.md + phase-N-<slug>.md format the dashboard ingests. Don't use it for ad-hoc todo lists or in-repo design docs.

Slash commands (8)

• /core:dashboard

  Session dashboard — tool usage, active tasks, agent stats, and metrics overview

• /core:find

  Find files by pattern across the project's repositories

• /core:impact

  Cross-repo impact analysis — graph-aware (Graft, then Graphify) with a live ripgrep fallback

• /core:land

  End-of-session landing ritual — close finished tasks, keep genuine WIP active, write a NEXT.md handoff, file follow-ups, and trim duplicated memory before you stop

• /core:new-feature-branch

  Branch-from-fresh-main boilerplate — checkout main, pull, create branch with a meaningful name, push empty so it can be protected

• /core:search

  Fast code search across the project's repositories using ripgrep

• /core:statusline-help

  Explain the custom statusline — what every line/field means, data source, colors, and the location knob

• /core:sweep-stale-flags

  Find feature flags, env vars, and config keys referenced in code but absent from env-check / settings — dead toggles that pretend to gate behaviour

Subagents (13)

• architect

  Design work before implementation — system architecture with trade-offs and rollout, API contracts and schemas, database schemas and safe migrations. Produces designs, not code.

• code-reviewer

  Read-only review of a diff, a change set, or a whole subsystem — correctness, silent failures, contract alignment, plan conformance, and code quality — returning severity-ranked file:line findings and a single machine-parseable verdict.

• debugger

  Root-cause analysis and minimal fixes — bugs, build and type errors, CI failures, and performance regressions. Diagnoses first, fixes surgically, proves the fix with a regression test.

• implementation-agent

  Execute code changes as a leaf executor (step_file input), or orchestrate step-by-step execution of a ready workspace plan (task_dir input) with per-step verification.

• planner

  Break work of any size into an executable workspace plan — phase docs with falsifiable acceptance criteria, self-contained executor prompts, and dependency sequencing the dashboard can track.

• researcher

  Read-only research and impact analysis — evaluate libraries and patterns against the project's stack, map how a change ripples through the code, and synthesize codebase context the built-in explorer can't judge.

• security-auditor

  Read-only security review — OWASP Top 10 sweep with evidence, STRIDE threat modeling on the project's domain, and severity-ranked findings ending in a machine-parseable verdict.

• system-improver

  Read a retrospective digest of the whole agent system and write an evidence-cited analysis of what hurts, why, and what to change across agents, skills, commands, hooks and processes.

• tech-lead

  Orchestrate development work — understand the task, surface unknowns, route by size to the right executors, gate quality with an independent review, and close with a summary.

• test-runner

  Execute the project's test suites and report pass/fail counts, failures with their actual output, and coverage — without writing or modifying tests.

• test-writer

  Write unit, integration, component, and E2E tests in the project's testing stack — tests that assert behavior, fail for the right reason, and run green before delivery.

• ui-developer

  Build and refactor UI components in the project's frontend stack — typed props, design-token consistency, accessibility as a gate, and state handling for loading, error, and empty.

• verification-agent

  Run the project's deterministic checks — build, typecheck, lint, tests, security scan — and report exactly what ran and what it said, ending in a machine-parseable verdict.

Hooks (23)

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/phase-guard.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/protect-sensitive-files.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/bash-shape-guard.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/prod-deploy-guard.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/search-scope-guard.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/architecture-freshness.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/agent-routing-guard.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/code-formatter.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/type-checker.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/post_bash_index_check.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/post-tool-observe.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-context-bridge.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/task-session-log.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/architecture-digest.sh

• SessionEnd

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-summary.sh

• SubagentStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/subagent-start.sh

• SubagentStop

  ${CLAUDE_PLUGIN_ROOT}/hooks/subagent-stop.sh

• PreCompact

  ${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact.sh

• PostCompact

  ${CLAUDE_PLUGIN_ROOT}/hooks/post-compact.sh

• Notification

  ${CLAUDE_PLUGIN_ROOT}/hooks/notify-completion.sh

• PreModelSwitch

  ${CLAUDE_PLUGIN_ROOT}/hooks/pre-model-switch.sh

• PostModelSwitch

  ${CLAUDE_PLUGIN_ROOT}/hooks/post-model-switch.sh