metraton
UserSecurity-first multi-agent orchestration plugin for Claude Code — classifies every command by risk, gates state-changing operations behind consent, injects project context, and routes work to specialist agents. One unified plugin.
Categories
Indexed Skills (37)
agent-approval-protocol
Use when constructing or interpreting the approval handoff envelope between subagent and orchestrator -- sealed_payload schema, approval_id format, APPROVAL_REQUEST contract shape, and reading a granted approval from the DB
agent-contract-handoff
Use when you need the exact field schema, required/conditional/optional status, or the trigger for any field of the agent_contract_handoff envelope -- input or output, top-level field, sub-field table, agent_state enum, or the JSON-not-YAML rule
agent-creation
Use when creating a new specialist agent for Gaia, or reviewing whether an existing agent follows the correct structure, tone, and component inventory
agent-response
Use when an agent returns an agent_contract_handoff response that needs to be interpreted and presented to the user
agentic-loop
Use when the orchestrator injects "Carga la skill agentic-loop" with a goal, eval_command, metric, and threshold
brief-spec
Use when the user wants to create a brief or spec for a feature before planning
gaia-patterns
Use when building or modifying Gaia components -- agents, skills, hooks, CLI tools, or routing config
gaia-planner
Use when planning features or decomposing work into tasks from a brief
gaia-release
Use when testing, validating, or publishing Gaia releases -- "install local", "pre-release", "dry-run", "release", RC, stable, plugin dry-run
gaia-verify
Use when the user wants to verify a Gaia installation -- "probemos", "verify", "test installation", "gaia-verify"
git-conventions
Use when creating a git commit or preparing changes for a pull request
memory
Use when reading, searching, saving, or curating Gaia memory — atoms, decisions, negative space, project/user/feedback notes — or when triaging the SessionStart Workspace Memory block
orchestrator-present-approval
Use when processing APPROVAL_REQUEST with approval_id from a subagent -- enforces showing values before asking for user consent
pending-approvals
Use when the user invokes approvals directly -- "ver pendientes", "aprobar P-XXXX", "rechazar P-XXXX", "approve P-", "reject P-"
security-tiers
Use when classifying any operation before executing it, or deciding whether user approval is required
subagent-request-approval
Use when a mutative command was blocked by the hook and you need to request user approval, or when presenting a plan for a T3 operation before executing it
coding-standards
Use when writing, editing, or reviewing code and its inline documentation — module headers, inline comments, docstrings, doc comments — in any language or stack
verification-oracle
Use when re-running a task_gates entry (or a proposed contract verification block) whose verification_type is `command` or `code`, to deterministically re-execute the declared check and compare the actual result against the gate's expected value -- not for `semantic` or `self_review` gates, which need judgment rather than re-execution.
verification-rubric
Use when judging a task_gates entry whose verification_type is semantic or self_review -- reading the gate's evidence_shape as an explicit rubric, assessing the produced work against each stated criterion, and emitting a justified pass/fail verdict. Loaded by the verifier role for judgment-based gates.
command-execution
Use when executing any bash command, CLI tool, or shell operation
diagram-builder
Use when the user wants to build or extend a diagram deck of nested sections and components authored in plain YAML — an architecture map, a timeline diagram, a planner board, a process-flow diagram, a slide-style presentation, a side-by-side comparison, or a mind-map. Not for charts, plots, or numeric/data visualization — route those to the dataviz skill. Triggers — "build a diagram", "architecture diagram", "diagram deck", "timeline diagram", "flow diagram", "planner board", "comparison diagram", "add a page/section/component to the diagram".
skill-creation
Use when creating a new skill, improving an existing skill, or deciding what a skill should contain and how it should be structured
blog-writing
Use when writing, drafting, or publishing a blog article for metraton.github.io
execution
Use when the user has approved a T3 operation and execution is about to begin
gaia-audit
Use when the user asks to audit, check, or review a Gaia component (an agent or a skill) against its standard and its live implementation -- "audita este skill", "chequea este agente", "¿está bien esta skill con la implementación?", "¿cómo mejoro este agente?"
gaia-compact
Use when the user asks to compact the current session -- "compacta", "compact", "oye Gaia compacta", "orquestador compacta", "haz un compact", "compactemos la sesión". Runs /compact with a structured prompt that preserves decisions, components, gaps, file map, and next steps.
gmail-policy
Use when managing Gmail messages, labels, or email workflows via gws CLI or Gmail MCP tools
gmail-triage
Use when the user wants to clean up, organize, or triage their Gmail inbox interactively
gws-setup
Use when installing or configuring the Google Workspace CLI (gws) for a Google account
investigation
Use when starting an investigation, analyzing existing code or infrastructure, or building findings before proposing changes
jira-ticket-writing
Use when creating or drafting Jira/Atlassian tickets or issues, or when standardizing ticket output for a project
readme-writing
Use when writing or updating a README for a Gaia component folder (agents/, skills/, hooks/, commands/, config/, bin/, tests/, build/, or the repo root)
scheduled-task
Use when the user wants something to run routinely / on a schedule rather than once now -- "tarea programada", "rutinariamente", "cada mañana", "cada N horas", "todas las noches", "schedule", "cron". Covers mounting, structuring, and running an unattended headless task that reports back, plus consuming its reports. NOT for a live in-session agentic loop (that is agentic-loop).
session-reflection
Use at the end of a session with substantial conversational work to offer the user a structured reflection before closing -- briefs closed, decisions taken, components modified
visual-verify
Use when about to declare done on any output with a visual surface -- an HTML page, a rendered UI, a diagram, a slide, a screenshot-able view -- to confirm by looking at the rendered result instead of asserting it. Also use when asked to screenshot or visually check a page or a local file.
agent-protocol
Use when producing any agent response
fast-queries
Use when diagnosing an issue, checking system health, or validating infrastructure state before starting a task
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.