Skip to content

LeoYeAI/agent-master-skills / skills/agent-harness

agent-harness

Verified

Use when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.

assets/harnesses/agent-launcher.json

View on GitHub
{
  "schema": "agent-harness/manifest.v1",
  "domain": "agent-launcher",
  "skill_count": 6,
  "loop_defaults": {
    "max_attempts_per_task": 3,
    "max_loop_iterations": 12,
    "escalate_on": [
      "attempts_exhausted",
      "no_verification_available",
      "destructive_or_irreversible_action",
      "goal_drift_detected"
    ]
  },
  "skills": [
    {
      "name": "agent-launcher-orchestrator",
      "path": "agent-launcher/skills/agent-launcher-orchestrator",
      "description": "Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an agent', 'run this nightly'). Reads the session goal, routes with goal_router.py and compiles the loop with loop_compiler.py.",
      "tools": [
        {
          "script": "agent-launcher/skills/agent-launcher-orchestrator/scripts/goal_router.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/agent-launcher-orchestrator/scripts/goal_router.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/agent-launcher-orchestrator/scripts/goal_router.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/agent-launcher-orchestrator/scripts/goal_state.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/agent-launcher-orchestrator/scripts/goal_state.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/agent-launcher-orchestrator/scripts/goal_state.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/agent-launcher-orchestrator/scripts/loop_compiler.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/agent-launcher-orchestrator/scripts/loop_compiler.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/agent-launcher-orchestrator/scripts/loop_compiler.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": true
      },
      "references": []
    },
    {
      "name": "grade-iterate",
      "path": "agent-launcher/skills/grade-iterate",
      "description": "Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds the outcome with outcome_builder.py, reads verdicts with verdict_reader.py and runs held-back evals from eval_scaffold.py.",
      "tools": [
        {
          "script": "agent-launcher/skills/grade-iterate/scripts/eval_scaffold.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/grade-iterate/scripts/eval_scaffold.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/grade-iterate/scripts/eval_scaffold.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/grade-iterate/scripts/outcome_builder.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/grade-iterate/scripts/outcome_builder.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/grade-iterate/scripts/outcome_builder.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/grade-iterate/scripts/verdict_reader.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/grade-iterate/scripts/verdict_reader.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/grade-iterate/scripts/verdict_reader.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "interview",
      "path": "agent-launcher/skills/interview",
      "description": "Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and writes a build sheet with build_sheet_builder.py, checked by primitives_validator.py; no API key needed.",
      "tools": [
        {
          "script": "agent-launcher/skills/interview/scripts/build_sheet_builder.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/interview/scripts/build_sheet_builder.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/interview/scripts/build_sheet_builder.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/interview/scripts/interview_planner.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/interview/scripts/interview_planner.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/interview/scripts/interview_planner.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/interview/scripts/primitives_validator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/interview/scripts/primitives_validator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/interview/scripts/primitives_validator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "run-without-you",
      "path": "agent-launcher/skills/run-without-you",
      "description": "Use when a graded managed agent should run on a schedule, on an event trigger or on demand ('run it every morning'). Validates cron with cron_validator.py and builds the deployment with deployment_builder.py.",
      "tools": [
        {
          "script": "agent-launcher/skills/run-without-you/scripts/cron_validator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/run-without-you/scripts/cron_validator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/run-without-you/scripts/cron_validator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/run-without-you/scripts/deployment_builder.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/run-without-you/scripts/deployment_builder.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/run-without-you/scripts/deployment_builder.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/run-without-you/scripts/next_directions_writer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/run-without-you/scripts/next_directions_writer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/run-without-you/scripts/next_directions_writer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "stage-launch",
      "path": "agent-launcher/skills/stage-launch",
      "description": "Use when a managed-agent build sheet is ready to launch ('launch it', 'deploy the agent'). Generates and validates API payloads with payload_generator.py and payload_validator.py and writes a resumable curl script with launch_script_writer.py that uses the user's own key.",
      "tools": [
        {
          "script": "agent-launcher/skills/stage-launch/scripts/launch_script_writer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/stage-launch/scripts/launch_script_writer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/stage-launch/scripts/launch_script_writer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/stage-launch/scripts/payload_generator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/stage-launch/scripts/payload_generator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/stage-launch/scripts/payload_generator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/stage-launch/scripts/payload_validator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/stage-launch/scripts/payload_validator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/stage-launch/scripts/payload_validator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "wrap-up",
      "path": "agent-launcher/skills/wrap-up",
      "description": "Use when closing out a launched managed agent ('wrap up', 'what do I own now'). Inventories primitives with primitives_inventory.py, regenerates the overview with overview_page.py and suggests next upgrades with upgrade_suggester.py.",
      "tools": [
        {
          "script": "agent-launcher/skills/wrap-up/scripts/overview_page.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/wrap-up/scripts/overview_page.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/wrap-up/scripts/overview_page.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/wrap-up/scripts/primitives_inventory.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/wrap-up/scripts/primitives_inventory.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/wrap-up/scripts/primitives_inventory.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "agent-launcher/skills/wrap-up/scripts/upgrade_suggester.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 agent-launcher/skills/wrap-up/scripts/upgrade_suggester.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 agent-launcher/skills/wrap-up/scripts/upgrade_suggester.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall