29 tagged agent governance, measured the same way as everything else here.
Browse within: copilot-agents 8copilot-instructions 8copilot-skills 8
Agent Claude Code
Audits DashClaw's drift-prone hardcoded counts and version stamps — SDK method counts (Node/Python), MCP tool/resource counts, route counts, and the unified platform+SDK version — against the live source of truth, and reports every mismatch with file:line. Use before shipping, after route/SDK changes, or whenever…
Agent Claude Code
Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the failures plus a pass/fail verdict. Use to verify a change without dragging multi-hundred-line build/test logs into the main thread. Delegate gate-running here instead of running it inline.
Agent Claude Code
Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repositories, API-key auth, x402 spend, webhooks, org/tenant scoping). Invoke before merging or shipping any diff that touches auth, API keys, x402/spend, webhooks, secrets/env, or database access. Reports findings…
Agent
Match the right skills, tools, and capability packages for a MetaKim agent or workflow.
Agent
Discover external tools and skills to close MetaKim capability gaps.
Agent
Design security boundaries, hooks, permissions, and rollback rules for MetaKim agents.
andreaswasita/copilot-agents-dojo
Agent
Designs system architecture, defines technical strategy, ensures long-term code quality, and owns the technical half of requirements engineering — system impact analysis, data flows, process modelling, and traceability from business intent to system design.
andreaswasita/copilot-agents-dojo
Agent
Owns TOGAF Phase A/B. Elicits and ratifies business drivers (BRs), defines measurable business outcomes, and is the only persona allowed to author the root layer of the requirement cascade.
andreaswasita/copilot-agents-dojo
Agent
Manages project planning, timeline coordination, and cross-team communication. Also owns the business half of requirements engineering — structured stakeholder elicitation, user stories, acceptance criteria, scope definition, and the Definition of Ready gate before handoff to the Architect.
Agent
Maintainer-facing index of all 737 artefacts in this package. Auto-generated from .agent-src.uncondensed/ and docs/guidelines/.
Agent
What happened. One paragraph, no log excerpts, no names. State the pattern, not the anecdote.
Agent
Agent-layer orchestrator — routes to init, optimize, audit. Covers AGENTS.md and its multi-tool stubs (CLAUDE.md, GEMINI.md, copilot-instructions.md, .cursorrules).
Agent Claude Code
Checks release readiness and packaging consistency.
Agent Claude Code
Reviews code for security vulnerabilities.
Agent
Read-only Postgres/database analyst. Answers questions by running SELECT-style reads and returning clean summaries — never raw dumps. Writes are hard-blocked by a PreToolUse guard hook. Use proactively whenever a task needs to query data and only needs to READ it. Do NOT use when the task must modify data or run a…
Agent Claude Code
Adapted from the TORQ Console harness (E:\TORQ-CONSOLE\.claude\agents). These are TorqClaw-local definitions. The Console harness drives a different product through .torq/launch/ watcher scripts and hardcoded E:\TORQ-CONSOLE\... paths; running those agents against this repo would read specs from and write verdicts…
aget-framework/template-advisor-aget
Agent Claude Code
Place subagent definition files here. Each .md file defines a specialized subagent that can be invoked via the Task tool or --agent flag.