atretyak1985

atretyak1985/swarmery

Plugin Claude Code

Plugin marketplace listing 12 plugins: core, uav-pack, iot-pack, web-pack, infra-pack.

atretyak1985/swarmery

Settings file Claude Code

The craft of agent swarms — a vendor-neutral, multi-project Claude Code agent framework (plugin marketplace): one shared core + opt-in domain packs.

atretyak1985/swarmery

Instructions file

Claude Code instructions for atretyak1985/swarmery, covering claude.md, what this repo is, commands, validate all json manifests and hook behavioral tests.

atretyak1985/swarmery

Plugin Claude Code

Multi-account pack: bind a project to one of several Claude Code accounts and run every session under it — /account, a shell wrapper, an optional shell function, and a wrong-account warning. Opt-in; REQUIRES the swarmery CLI on the machine (every decision lives in swarmery account, so the shell surfaces and the daemo.

atretyak1985/swarmery

Command

Thin entry point for /account [list|use |clear|setup-shell [--uninstall]] — shows which Claude Code account this project runs under and switches it. Every decision lives in the swarmery account CLI; no run logic lives here.

atretyak1985/swarmery

Hook

Runs when a session starts, executing warn-wrong-account.sh. From atretyak1985/swarmery.

atretyak1985/swarmery

Plugin Claude Code

Architecture-map pack: the /architecture-map skill — generate a repo-wide architecture map as architecture-out/architecture-map.json (machine contract with layers, modules, and file-anchored flows for AI agents) plus a self-contained architecture-map.html viewer. Freshness-stamped per commit with incremental refresh…

atretyak1985/swarmery

Skill Claude CodeCodex

Generate or refresh the repo-wide architecture map — architecture-out/architecture-map.json (machine contract with named flows) + architecture-map.html (self-contained viewer). Use when the user asks for an architecture map, repo map, "/architecture-map", or when an agent needs a fresh machine-readable architecture…

atretyak1985/swarmery

Plugin Claude Code

Claude-engineering domain pack: best-practice skills for building and auditing Claude agent systems — agent architecture, tool/MCP design, prompt engineering, Claude Code configuration, and context reliability. Opt-in; requires core.

atretyak1985/swarmery

Skill Claude CodeCodex

Use when designing or reviewing Claude-based agent systems — agentic loops and stopreason handling, multi-agent orchestration, coordinators, subagent invocation and context passing, workflow enforcement, Agent SDK hooks (PreToolUse/PostToolUse), task decomposition, or session state and resumption. Also when an agent…

atretyak1985/swarmery

Skill Claude CodeCodex

Use when setting up or auditing Claude Code in a repository — CLAUDE.md hierarchy and imports, .claude/rules, custom slash commands and skills, path-specific rules, plan mode vs direct execution, iterative refinement workflow, or CI/CD integration with headless -p mode. Also when instructions get ignored, conventions…

atretyak1985/swarmery

Skill Claude CodeCodex

Use when creating or reviewing tool definitions for Claude — tool names, descriptions, input schemas, structured error responses, toolchoice configuration, MCP server setup and scoping, or built-in tool usage (Grep, Glob, Read, Edit). Also when Claude picks the wrong tool, confuses similar tools, retries hopeless…

atretyak1985/swarmery

Skill Claude CodeCodex

Use when writing or reviewing system prompts, few-shot examples, structured output via tool use, JSON schema validation with retry loops, Message Batches API processing, or multi-instance/multi-pass review pipelines such as automated PR reviewers. Also when outputs are inconsistent between runs, JSON fails validation…

atretyak1985/swarmery

Skill Claude CodeCodex

Use when reviewing long-running or multi-agent Claude systems for reliability — context window management and summarisation, escalation and ambiguity resolution, error propagation between agents, codebase exploration and context degradation, human review and confidence calibration, or information provenance and…

atretyak1985/swarmery

Plugin Claude Code

Vendor-neutral agent-development core: generic orchestration, planning, quality, and specialist agents plus reusable skills, commands, hooks, and the project-aware agent-work CLI.

atretyak1985/swarmery

Agent

Design REST route handlers, Zod schemas, SSE endpoints, and server actions when orchestrator needs API contract design before implementation.

atretyak1985/swarmery

Agent

Design system architecture with component diagrams, trade-off analysis, and rollout plans when orchestrator needs multi-component coordination design.

atretyak1985/swarmery

Agent

Fix build, TypeScript, and compilation errors with minimal diffs; no refactoring.

atretyak1985/swarmery

Agent

Produce CI pipeline failure forensics with three-tier remediation plans from job traces.

atretyak1985/swarmery

Agent

Audit an inherited/live system in risk order (access & inventory → security → operational readiness → selective code). Emit a prioritized P0-P3 remediation backlog (Stop-the-bleeding → Safety-net → Structural-debt → Nice-to-have) where every finding is What→Risk/Cost→Fix→How-to-verify, plus a 1-10 health score and…

atretyak1985/swarmery

Agent

Generate conventional commit messages with project-specific scopes (project.json → commitScopes) from staged changes.

atretyak1985/swarmery

Agent

Parallel context gathering for Phase 2 using semantic and exact-match search across the project's repos.

atretyak1985/swarmery

Agent

Trace data types across the 5-layer contract chain (DB schema→Actions→Zod→API→Frontend+device) and emit VALID/WARN/FAIL verdict when orchestrator runs Phase 5 Quality Gate.

atretyak1985/swarmery

Agent

Design PostgreSQL schemas, SQL migration files, and matching ORM schema definitions when orchestrator needs schema changes in Phase 3.5 or task-planner identifies DB work.