components
01Command
Complete reference for tracking software components — add, update, search, deprecate, undeprecate, and remove.
157 tagged ai coding agents, measured the same way as everything else here.
Browse within: agentic-development 34brownfield 34ci-cd 34code-quality 34agent-memory 20ai-memory 20agent-harness 18agent-orchestration-as-code 18agentic-workflows 18ai-governance 18developer-workflows 18golang 18opencode 18agents-md 16
Command
Complete reference for tracking software components — add, update, search, deprecate, undeprecate, and remove.
Command
Complete reference for all goal-related commands — definition, refinement, execution, review, codification, and management.
Command
Complete reference for managing relationships between entities in the knowledge graph.
aws-samples/sample-well-architected-skills-and-steering
Command
Perform a full AWS Well-Architected Framework review of the user's workload by analyzing code, IaC, and configurations to produce evidence-backed findings with prioritized remediation.
aws-samples/sample-well-architected-skills-and-steering
Command
Assess a workload's readiness to migrate to AWS by analyzing existing code, dependencies, configurations, and infrastructure to produce evidence-backed findings covering the 7 Rs, risks, and a migration plan.
aws-samples/sample-well-architected-skills-and-steering
Command
Generate preventive Well-Architected guardrails — AWS Config rules, Service Control Policies, permission boundaries, CloudWatch alarms, and IaC policy checks (CDK Aspects, cfn-guard, OPA/Sentinel) — so a workload stays aligned with Well-Architected best practices over time instead of being assessed once.
jcarlosrodicio/opencode-agent-orchestration-kit
Command
Run a bounded, locally verifiable autonomous engineering workflow.
jcarlosrodicio/opencode-agent-orchestration-kit
Command
Run an optional AHE iteration to evaluate or improve this OpenCode harness with evidence and attribution.
jcarlosrodicio/opencode-agent-orchestration-kit
Command
Design and run a bounded engineering loop with durable state, human approval, and independent verification.
Command
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
Command
Spawn N concurrent /ai-sdlc execute sessions in tmux panes (max 5). Reads the dispatch-ready frontier, presents top N candidates, asks operator to confirm, then fires one tmux window per task. Coordination via .ai-sdlc/dispatch/sessions/. Resource-gated: refuses if available memory = ncpu. AISDLC-462.
Command
Run one autonomous orchestrator tick in the current Claude Code session as Conductor (RFC-0041 §4.2).
Command
SkillNote dashboard — see active collection, skills, and available commands.
Command
ovd-go — orient on the active leaf and continue execution.
Command
ovd-log — lightweight save (default) or full handoff at session end.
Command
ovd-plan — deliberate, edit, or surface a new idea against the project plan.
Command
Per-finding suppression with a typed-category audit trail. The allowlist is dxkit's deliberate escape hatch for findings you can't fix today: false positives, intentional test-fixture patterns, real risks mitigated externally, or work you're deferring with an explicit deadline.
Command
Diff a current scan against a committed baseline and classify each finding as added / relocated / toolingdrift / configdrift / persisted / removed / fixed. Block on net-new regressions per the brownfield policy; exit non-zero so a pre-commit hook, pre-push hook, or CI workflow can stop the commit/push/merge.
Command
Close the debt the deterministic lanes cannot version-bump away: the grandfathered broken build, advisories with no direct upgrade path, the lint backlog, missing tests, missing docs. Each run plans that debt as finite work orders and works them in two tiers: deterministic recipes execute first at $0 (lockfile resync…
Command Claude Code
Spike a design idea — decode brief/screenshot/figma, scaffold shadcn into /sandbox, optionally layer motion. Default entry point for any design exploration.
Command
Consolidate terminal IDD artifacts into the roll-up ledger — classify mode produces a reviewable archive manifest; apply mode tags, distills to docs/idd-ledger.yaml, and deletes the archived files.
Command
Chart a phase-0 Exploration map from a loose idea too foggy for /interview — name the destination, sketch the fog, create decision tickets.
Command
Run an adversarial gap-check on one or more Specs before execution — verifies completeness preconditions, simulates the implementing agent, reports Blocker/Warning findings, and performs a coverage/omission sweep.
Command
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.