claude

agent-orchestration-workbench

Specialized subagents for multi-agent architecture, deterministic testing, reliability review, security audit, incident triage, and evaluation design.

1 on GitHubby Lucas-Belucci-Belliniv0.1.0See repository LICENSE and individual source noticesupdated 13 days agodevelopment
/

Plugin agent-orchestration-workbench from marketplace all-skills-for-the-claude-code in Lucas-Belucci-Bellini/All-Skills-for-the-claude-code. Commands read from the repo's manifest — 12 days ago.

What it installs

Slash commands (4)

  • /agent-orchestration-workbench:incident-review

    Reconstructs an agent workflow incident from logs and state evidence without performing repair or replaying live work.

  • /agent-orchestration-workbench:orchestration-plan

    Creates an evidence-based plan for a multi-agent implementation without modifying files or executing side effects.

  • /agent-orchestration-workbench:release-gate

    Prepares an evidence-backed go or no-go review for a candidate change without publishing or merging it.

  • /agent-orchestration-workbench:verification

    Runs a bounded verification workflow for agent changes using reproducible tests and independent read-only reviews.

Subagents (6)

  • agent-evaluation-designer

    Designs reproducible evaluations for agent workflows, including task-level success criteria, adversarial cases, baseline comparisons, and uncertainty reporting. Use before claiming an agent change improved quality or reliability.

  • agent-security-auditor

    Audits agent workflows for prompt injection, excessive tool authority, secret leakage, unsafe delegation, and unapproved side effects. Use before enabling new tools, agents, integrations, or autonomous actions.

  • orchestration-architect

    Designs and reviews multi-agent execution architectures, task graphs, state contracts, deadlines, retries, and recovery boundaries. Use before implementation or when responsibilities, concurrency, or failure semantics are unclear.

  • orchestration-incident-triager

    Reconstructs failed or stalled agent runs from logs, event IDs, state records, and artifact receipts. Use when the cause, ordering, or completion status is uncertain.

  • orchestration-runtime-reviewer

    Reviews orchestration code for state-machine bugs, race conditions, duplicate execution, unsafe retries, and false success reporting. Use for an independent read-only review before accepting a workflow change.

  • orchestration-test-engineer

    Creates and runs deterministic tests for agent orchestration, including state transitions, concurrency races, delayed callbacks, retries, and recovery. Use when implementation behavior needs reproducible regression coverage.

View source on GitHub

More from Lucas-Belucci-Bellini/All-Skills-for-the-claude-code

All 4 plugins →

all-skills-collection

claude

Install the unified collection of 2565 distinct skills, all authored, covering all 31 profile languages and specialist engineering workflows.

200 skills

1

artifact-analysis-workbench

claude

Repository-to-skill synthesis: source inventory, capability mining, provenance, semantic deduplication, routing evaluation, and release gates.

15 skills · 10 agents

1

skill-library-maintainer

claude

Audit, organize, deduplicate and update the skill library, then prepare reviewed pull requests.

1 skill · 2 commands

1

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

cli-anything

claude

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

5 commands

HKUDS/CLI-Anything 58,665

Maintain agent-orchestration-workbench?

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 plugins4 plugins