Real Skill packageSource verifiedClawHub registry

SKILL

FDE Skill——帮 FDE（前线部署工程师）更好完成企业 AI 落地的方法论 Skill。约束 Agent 行为、审计每次变更、沉淀经验。 底层实现叫约束层（Harness）——一个层四种能力：注入·审计·回溯·进化。FORGE 自迭代工具链是内部开发工具。 内置持续优化模式（sustain），自动读 audit 报告趋势生成优化报告。

Identity and source

Publisher attributionKongFangXunregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction bundle27 recorded files
Canonical sourceClawHub registryclawhub:kongfangxun:sofagent
Open canonical source ↗

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.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/13/2026.claude/skills/sofagent

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/13/2026.agents/skills/sofagent

Runtime, 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/sofagent

Runtime, 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 @kongfangxun/sofagent
clawhub inspect @kongfangxun/sofagent --version 1.3.3

Security evidence

SkillVetAI static result: high signal

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
full text content
Files
27 / 27 inspected as text
Checked
8/13/2026, 9:39:53 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highRemote content is piped directly to a shellharness/entry-gate.md:20 · confidence 98%curl\|bash
1 High/Critical review queue entry
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
Open human review queue →
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
2 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
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, 4:00:06 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 hashsha256:91fb0baac7a2b4159d8b8a36c71ac596238df81f4cc006b948d5786936b34e7c
Show up to 27 recorded paths
  • AGENTS.md
  • agents/audit/SKILL.md
  • agents/engineer/SKILL.md
  • agents/fde/SKILL.md
  • agents/reviewer/SKILL.md
  • core-rules.md
  • custom/README.md
  • harness/engage-fde.md
  • harness/engage.md
  • harness/entry-gate.md
  • harness/fde-template.md
  • harness/knowledge-maintain.md
  • harness/loop-check.md
  • harness/loop-evaluate.md
  • harness/loop-exit.md
  • harness/task-aware.md
  • harness/task-closure.md
  • role-audit.md
  • role-fde.md
  • role-orchestrate.md
  • skill-card.md
  • SKILL.md
  • skills/01-entry.md
  • skills/02-discovery.md
  • skills/03-quantify.md
  • skills/04-deliver.md
  • skills/05-exit.md

Source changelog

v1.3.3: L2 团队协作 + Refine Agent + 进化闭环 + evidence