LeoYeAI/agent-master-skills / skills/agent-harness
agent-harness
VerifiedUse 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/compliance-os.json
View on GitHub{
"schema": "agent-harness/manifest.v1",
"domain": "compliance-os",
"skill_count": 9,
"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": "ai-act-readiness",
"path": "compliance-os/skills/ai-act-readiness",
"description": "Use for /compliance-os:ai-act-readiness, or EU AI Act readiness questions during AI-system intake or before EU deployment.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "aims-audit",
"path": "compliance-os/skills/aims-audit",
"description": "Use for /compliance-os:aims-audit, or ISO 42001 readiness before stage 1 or an internal audit cycle.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "compliance-os",
"path": "compliance-os/skills/compliance-os",
"description": "Use when running several compliance frameworks at once: which apply, where controls overlap, a mock audit or one evidence checklist. Runs framework_selector.py, cross_framework_mapper.py, audit_simulator.py and evidence_pool_generator.py.",
"tools": [
{
"script": "compliance-os/skills/compliance-os/scripts/audit_simulator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 compliance-os/skills/compliance-os/scripts/audit_simulator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "compliance-os/skills/compliance-os/scripts/cross_framework_mapper.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 compliance-os/skills/compliance-os/scripts/cross_framework_mapper.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "compliance-os/skills/compliance-os/scripts/evidence_pool_generator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 compliance-os/skills/compliance-os/scripts/evidence_pool_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "compliance-os/skills/compliance-os/scripts/framework_selector.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 compliance-os/skills/compliance-os/scripts/framework_selector.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"audit_simulation_methodology.md",
"compliance_os_pattern.md",
"cross_framework_overlap.md",
"evidence_artifact_reuse_index.md",
"evidence_management.md",
"multi_framework_audit_playbook.md"
]
},
{
"name": "compliance-readiness",
"path": "compliance-os/skills/compliance-readiness",
"description": "Use for /compliance-os:compliance-readiness, or before adding a framework or planning the annual audit calendar.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": false,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "fda-qsr-audit-prep",
"path": "compliance-os/skills/fda-qsr-audit-prep",
"description": "Use for /compliance-os:fda-qsr-audit-prep, or before an FDA inspection, QMSR internal audit or Form 483 response.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "gdpr-audit-prep",
"path": "compliance-os/skills/gdpr-audit-prep",
"description": "Use for /compliance-os:gdpr-audit-prep, or before a GDPR review, post-breach audit or DPA investigation.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "iso13485-audit-prep",
"path": "compliance-os/skills/iso13485-audit-prep",
"description": "Use for /compliance-os:iso13485-audit-prep, or before an ISO 13485 internal audit or DHF closure.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "iso27001-audit-prep",
"path": "compliance-os/skills/iso27001-audit-prep",
"description": "Use for /compliance-os:iso27001-audit-prep, or before an ISO 27001 internal, surveillance or stage 1 audit.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": false,
"loop_discipline": false,
"close_out": false
},
"references": []
},
{
"name": "soc2-audit-prep",
"path": "compliance-os/skills/soc2-audit-prep",
"description": "Use for /compliance-os:soc2-audit-prep, or before or during a SOC 2 Type II observation period.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": false,
"loop_discipline": false,
"close_out": false
},
"references": []
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |