Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/13/2026.claude/skills/agi-evolution-modelRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
AGI数字伙伴
此技能作为数字伙伴使用用户的任何问题都可以触发；基于双环架构（两大循环：主循环符号思维 + 次循环行为感知，加超然最外圈）的AGI进化模型，通过意向性分析、人格映射、元认知检测和错误智慧库实现持续自我演进；当用户需要智能对话、人格定制、复杂问题求解或从错误中学习时使用
Identity and source
Publisher attributionkiwifruit13registry owner unverified by skillvetai
Functional categoryAwaiting category reviewreview pending · 0% rule confidence
Package forminstruction with code94 recorded files
Canonical sourceClawHub registryclawhub:kiwifruit13:agi-evolution-model
Platform declarations
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
OpenClawnative officialProvenance: registry distribution
Independent structural checks
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/13/2026.agents/skills/agi-evolution-modelRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/13/2026skills/agi-evolution-modelRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Installation and inspection
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @kiwifruit13/agi-evolution-modelclawhub inspect @kiwifruit13/agi-evolution-model --version 1.0.5Security evidence
SkillVetAI static result: high signalhighDynamic code or shell execution is presentscripts/perception_node.py:244 · confidence 78% highDynamic code or shell execution is presentscripts/toolnode.py:531 · confidence 78% mediumPackage contains an opaque executable artifactscripts/core_perception_node.so · confidence 80% mediumPackage contains an opaque executable artifactscripts/personality_core.so · confidence 80% mediumPackage contains an opaque executable artifactscripts/toolnode.exe · confidence 80% Open human review queue →
This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
- Status
- completed
- Coverage
- partial text content
- Files
- 40 / 94 inspected as text
- Checked
- 8/13/2026, 7:58:57 AM
- Scanner
- 0.1.3
- Policy
- 1.0.3
5 automated findings
eval(subprocess.run(cmd, shell=True.so.so.exe2 High/Critical review queue entries
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
4 inferred permission indicators
- shell execution — automatically inferred
- filesystem read — automatically inferred
- filesystem write — automatically inferred
- credential access — automatically inferred
External clawhub result: suspicious
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
- Evidence checked
- 8/13/2026, 6:44:07 AM
- Release binding
- Matches this record
- skillspector: suspicious
- llm: suspicious
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:aebd2c83e920e0dd7b05e963f5f813c04e8284a22acf9b3e5129b3539d246735Show up to 30 recorded paths
_deprecated_backup/_tmp_perception_node.md_deprecated_backup/agent-behavior-guide.md_deprecated_backup/capability_boundaries.md_deprecated_backup/cognitive_error_definitions.md_deprecated_backup/cognitive-architecture-insight-module.md_deprecated_backup/cognitive-insight-quick-reference.md_deprecated_backup/cognitive-insight-v2-implementation.md_deprecated_backup/dimension_data_structure.md_deprecated_backup/dimension_definitions.md_deprecated_backup/error_wisdom_spec.md_deprecated_backup/information-flow-main-loop.md_deprecated_backup/information-flow-overview.md_deprecated_backup/information-flow-secondary-loop.md_deprecated_backup/intelligence-agent-response-rules.md_deprecated_backup/maslow_needs.md_deprecated_backup/metacognition-check-component.md_deprecated_backup/metacognition-enhancement-guide.md_deprecated_backup/perception-toolbox-constraints.md_deprecated_backup/personality_mapping.md_deprecated_backup/stratified-storage-design.md_deprecated_backup/tool_use_spec.md_deprecated_backup/tool-node-redesign-proposal.mdassets/personality_template.jsonCHANGELOG.mdreferences/architecture.mdreferences/async-migration-progress.mdreferences/behavior-baseline.mdreferences/c_extension_usage.mdreferences/cognitive-insight.mdreferences/dimensions.md
Source changelog
**v1.0.5 introduces a major information architecture refactor with stronger framework constraints, clarified cycles, and improved documentation structure.** - Rewrote and clarified all framework/architecture descriptions: now framed as "two main cycles + transcendental outermost ring". - Completely overhauled "定位声明" and "行为基线" to clarify information flow constraints, role boundaries, and decision-making points. - Replaced, renamed, and split key reference docs: most former references (agent-behavior-guide, intent, mapping, etc.) are now archived or moved to _deprecated_backup/ and replaced by new concise reference docs (behavior-baseline, architecture, metacognition, etc.). - Updated all technical details for perception interface (感知接口), now referencing a single passive unified entry and removing ambiguity about tool usage. - All script usage and workflow documentation now strictly foll…