Plugin Claude Code
Security-first multi-agent orchestration for Claude Code. Distributes the Gaia plugin: specialized agents across the development lifecycle with codebase-aware context injection and risk-classified command gating.
Plugin Claude Code
Security-first multi-agent orchestration for Claude Code. Agents span the full lifecycle; commands are risk-classified — reads run free, state changes need approval, irreversible ops blocked.
Agent
Use when inspecting, diagnosing, or validating the actual state of running systems — pods, services, logs, cloud resources, network connectivity, SSH access — or when comparing what IS running against what SHOULD be running (drift between live state and IaC/desired-state).
Agent
Use when writing, modifying, debugging, or reviewing application code, CI/CD pipelines, or developer tooling — or when investigating an application-layer bug or behavior.
Agent
Use as the orchestrator's workspace operator, executing adjudicated operations or batches when no domain specialist owns the artifact.
Agent
Use when a user prompt arrives in Gaia and needs routing, coordinated execution across specialist surfaces, informed-consent presentation, or synthesis of specialist contracts into one decision.
Agent
Use when planning a feature or decomposing work from a brief into an executable plan -- turning objectives and acceptance criteria into ordered, testable tasks ready for dispatch.
Agent
Use when building, modifying, or auditing Gaia's own machinery — agents, skills, hooks and hook modules, routing config, CLI plugins, build manifests — or when analyzing Gaia's architecture, install, or release surface. Not for work in the user's application, infrastructure, cluster, or live runtime.
Agent
Use when a task's gates are ready to be independently confirmed -- dispatched directly when a producing agent's contract proposes agentstate NEEDSVERIFICATION, never by surface-signal routing. Loads verification-oracle for command/code gates and verification-rubric for semantic/selfreview gates, then is the only role…
Agent
Use when creating, modifying, or reviewing the desired state of a Kubernetes cluster declared in Git — Flux HelmReleases, Argo Applications, Kustomizations, Helm values, manifests, ConfigMaps, Ingress — or when reasoning about reconciliation and drift between Git and the running cluster.
Agent
Use when provisioning, modifying, validating, or reviewing infrastructure-as-code — Terraform, Terragrunt, Pulumi, CloudFormation, OpenTofu, or CDK — including plan/apply workflows, state, and cloud resource declarations (IAM, VPC, buckets, service accounts).
Hook
Runs before the agent uses a tool for Bash, Task, Agent, SendMessage, Read, Edit, Write, Glob, Grep, WebSearch, WebFetch and NotebookEdit tool calls, executing pre_tool_use.py via python3 (5 commands). From metraton/gaia.
Hook
Runs after a tool call finishes for Bash, Task and AskUserQuestion tool calls, executing post_tool_use.py via python3 (3 commands). From metraton/gaia.
Hook
Runs when a subagent finishes, executing subagent_stop.py via python3. From metraton/gaia.
Hook
Runs when a session starts on startup, resume and compact, executing session_start.py via python3. From metraton/gaia.
Hook
Runs when a session ends, executing session_end_hook.py via python3. From metraton/gaia.
Hook
Runs before the context is compacted, executing pre_compact.py via python3. From metraton/gaia.
Hook
Runs after the context is compacted, executing post_compact.py via python3. From metraton/gaia.
Hook
Runs when the agent finishes a response, executing stop_hook.py via python3. From metraton/gaia.
Hook
Runs when a task is marked completed, executing task_completed.py via python3. From metraton/gaia.
Hook
Runs when a subagent starts, executing subagent_start.py via python3. From metraton/gaia.
Hook
Runs when you submit a prompt, before the agent sees it, executing user_prompt_submit.py via python3. From metraton/gaia.
Skill Claude CodeCodex
Use for approvalrequest, COMMANDSET, approval identifiers, fingerprints, and progress data.
Skill Claude CodeCodex
Use for the exact input/output schema and validation rules of agentcontracthandoff.