Skip to content

seb1n/awesome-ai-agent-skills / agent-engineering/human-in-the-loop

human-in-the-loop

Verified

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

FileKindSize
SKILL.mdskill md9.9 KB
agents/openai.yamlconfig232 B
assets/approval-policy-template.jsonconfig2.5 KB
references/gate-design-guide.mdmarkdown6.1 KB
scripts/validate_gate_policy.pyexecutablescript22.6 KB

assets/approval-policy-template.json

View on GitHub
{
  "workflow": "replace-with-workflow-name",
  "policy_version": "1.0.0",
  "policy_owner_subject": "policy-owner",
  "policy_approval_reference": "CHANGE-REPLACE-ME",
  "default": "deny",
  "roles": [
    "operator",
    "manager",
    "audit-owner"
  ],
  "approver_subjects": [
    {
      "subject_id": "policy-owner",
      "roles": [
        "audit-owner"
      ]
    },
    {
      "subject_id": "manager-a",
      "roles": [
        "manager"
      ]
    },
    {
      "subject_id": "manager-b",
      "roles": [
        "manager"
      ]
    }
  ],
  "decision_log_fields": [
    "event_id",
    "proposal_id",
    "proposal_digest",
    "policy_version",
    "requester_subject",
    "approver_subject",
    "approver_role",
    "decision",
    "decided_at",
    "escalation_event",
    "execution_authorization_decision",
    "audit_outage_state",
    "compensation_state",
    "break_glass_event"
  ],
  "waivers": [],
  "gates": [
    {
      "id": "material-action",
      "action_pattern": "resource.commit",
      "risk_tier": "high",
      "when": {
        "all": [
          {
            "field": "effect",
            "op": "eq",
            "value": "external"
          },
          {
            "field": "target.classification",
            "op": "in",
            "value": [
              "internal",
              "confidential",
              "restricted"
            ]
          }
        ]
      },
      "required_approver_roles": [
        "manager"
      ],
      "quorum": 1,
      "minimum_distinct_subjects": 1,
      "requester_may_approve": false,
      "evidence": [
        "target",
        "normalized_parameters",
        "proposal_digest",
        "expected_effect",
        "provenance"
      ],
      "expires_in_seconds": 1800,
      "on_timeout": "escalate",
      "escalation": {
        "after_seconds": 900,
        "to_roles": [
          "manager"
        ],
        "max_attempts": 2,
        "on_exhausted": "deny"
      },
      "audit_outage": {
        "behavior": "fail-closed",
        "notify_subjects": [
          "policy-owner"
        ]
      },
      "reauthorization": {
        "required_at_execution": true,
        "invalidation_events": [
          "role-change",
          "policy-change",
          "proposal-change",
          "target-state-change",
          "expiry"
        ]
      },
      "compensation": {
        "mode": "manual",
        "owner_subject": "policy-owner",
        "procedure_reference": "RUNBOOK-REPLACE-ME"
      },
      "break_glass": {
        "enabled": false
      },
      "waiver_ids": []
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall