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/c-level-agents.json

View on GitHub
{
  "schema": "agent-harness/manifest.v1",
  "domain": "c-level-agents",
  "skill_count": 22,
  "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": "boardroom",
      "path": "c-level-agents/skills/boardroom",
      "description": "Use for /c-level-agents:boardroom, or a decision spanning several executive domains (a pricing change, raise vs cut). Runs a 6-phase C-suite deliberation and writes a board memo.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": true
      },
      "references": []
    },
    {
      "name": "brief",
      "path": "c-level-agents/skills/brief",
      "description": "Use for /c-level-agents:brief, or to frame a strategic question (options, assumptions, success criteria) as a one-page brief before deliberation.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": true
      },
      "references": []
    },
    {
      "name": "c-level-agents",
      "path": "c-level-agents/skills/c-level-agents",
      "description": "Use when the founder wants a virtual executive team or a /c-level-agents command. Lists the 13 C-suite agents and 21 commands and routes multi-role decisions.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "caio-review",
      "path": "c-level-agents/skills/caio-review",
      "description": "Use for /c-level-agents:caio-review, or to challenge a plan involving AI (no eval set, API vs fine-tune vs self-host, EU AI Act class).",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cco-review",
      "path": "c-level-agents/skills/cco-review",
      "description": "Use for /c-level-agents:cco-review, or to challenge a plan touching retention, segmentation or CS headcount.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": true
      },
      "references": []
    },
    {
      "name": "cdo-review",
      "path": "c-level-agents/skills/cdo-review",
      "description": "Use for /c-level-agents:cdo-review, or to challenge a plan touching training-data rights, data architecture or data monetization.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cfo-review",
      "path": "c-level-agents/skills/cfo-review",
      "description": "Use for /c-level-agents:cfo-review, or to challenge a plan that commits real money (a hiring wave, a raise, a channel budget).",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "ciso-review",
      "path": "c-level-agents/skills/ciso-review",
      "description": "Use for /c-level-agents:ciso-review, or to challenge a plan touching customer data, compliance or production access.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cmo-review",
      "path": "c-level-agents/skills/cmo-review",
      "description": "Use for /c-level-agents:cmo-review, or to challenge positioning, ICP, messaging or channel mix before a launch.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cpo-review",
      "path": "c-level-agents/skills/cpo-review",
      "description": "Use for /c-level-agents:cpo-review, or to challenge a roadmap, a PMF claim or a feature-kill decision.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cro-review",
      "path": "c-level-agents/skills/cro-review",
      "description": "Use for /c-level-agents:cro-review, or to challenge a forecast, win-rate drop or sales-team scale-up.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cross-eval",
      "path": "c-level-agents/skills/cross-eval",
      "description": "Use for /c-level-agents:cross-eval, or when a high-stakes memo needs independent review by several models before the boardroom.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "cto-review",
      "path": "c-level-agents/skills/cto-review",
      "description": "Use for /c-level-agents:cto-review, or to challenge an architecture commitment, a 10x scaling plan or rebuild vs buy.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "decide",
      "path": "c-level-agents/skills/decide",
      "description": "Use for /c-level-agents:decide, or right after the founder approves a boardroom memo, to log it as a durable decision.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "execute",
      "path": "c-level-agents/skills/execute",
      "description": "Use for /c-level-agents:execute, or to turn an approved decision into a 90-day plan with weekly milestones and owners.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "founder-mode",
      "path": "c-level-agents/skills/founder-mode",
      "description": "Use for /c-level-agents:founder-mode, or any founder strategy question that hasn't been routed yet. Sends it to the right C-suite advisor or the boardroom.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "freeze",
      "path": "c-level-agents/skills/freeze",
      "description": "Use for /c-level-agents:freeze, or to put a cooling-off lock on an irreversible decision made under pressure.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "gc-review",
      "path": "c-level-agents/skills/gc-review",
      "description": "Use for /c-level-agents:gc-review, or to challenge a term sheet, customer MSA, IP assignment or regulatory exposure before signing.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "office-hours",
      "path": "c-level-agents/skills/office-hours",
      "description": "Use for /c-level-agents:office-hours, or when a founder question is too vague to route. Asks six YC-style questions before any advice.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "onboard",
      "path": "c-level-agents/skills/onboard",
      "description": "Use for /cs-onboard, or when the virtual C-suite lacks company context. Interviews the founder and writes ~/.claude/company-context.md.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "post-mortem",
      "path": "c-level-agents/skills/post-mortem",
      "description": "Use for /c-level-agents:post-mortem, or when a decision hits its 90-day review or kill criteria. Scores it against the original assumptions and dissent.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": false,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "vpe-review",
      "path": "c-level-agents/skills/vpe-review",
      "description": "Use for /c-level-agents:vpe-review, or to challenge a plan touching delivery speed, eng hiring, team structure or on-call.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "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