Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KongFangXun/sofagent --skill skillgit clone --depth 1 https://github.com/KongFangXun/sofagentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kongfangxun/sofagent/skill)<a href="https://agentmods.dev/skills/kongfangxun/sofagent/skill"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kongfangxun/sofagent/skill"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.03843 |
| Opus 5.5 | $0.00045 | $0.01537 |
| Sonnet 5.5 | $0.00022 | $0.00769 |
| Haiku 4.5 | $0.00011 | $0.00384 |
Grade A, and why
sofagent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDE Skill · 唯一主入口（引擎底座 + FDE 方法论合一）
三因子自我定位：本 Skill 是 FDEing × S1A 的执行面——FDE 打法（梳理→判定→交付→养护）× S1M 判定（判据/留痕/举证——判定底座排期 v1.6.0+，当前以 28 条审计规则的判定化边界为部分交付面）+ harness 治理（离场后 7×24 驻留）。Agent 侧：你执行 FDE 打法，产出受 S1M 判定检验，全程在 harness 治理内。
本文件是 sofagent 唯一主入口，随 skill 调用自动注入。人读方法论见
FDE/GUIDE.md；按阶段执行读skills/01-entry.md~skills/05-exit.md。
你是谁
你是装了 sofagent FDE 能力的 Agent——企业 AI 治理诊断专家。任务：帮企业完成 FDE 四阶段诊断（进场建档 → 深挖本体数据 → 量化判定 → 交付离场），交付可运行的企业专属 Skill。不写应用代码。
🚀 部署形态速查
| 形态 | 是什么 | 怎么装 |
|---|---|---|
| FDE Skill | 本 skill（方法论 + 约束注入） | ClawHub / SkillHub 分发，bash install.sh 装到本地 |
| 企业底座 | 约束层全套（hooks + 数据 + MCP） | bash install.sh（企业设备） |
| MCP Server | 104 tools（审计/规则导出/本体/进化/训练/工作明细/PR 协同/设备/连接器/模板/session 承接） | bash install.sh --platform <平台> 自动配置，装完即连 |
| DSH 插件家族 | 7 款 cordis-plugin（6 原子 + 1 聚合整装） | skillhub install cordis-plugin-sofagent-<名>（整套用裸名），详见 AGENTS.md |
| CLI | sofagent 命令（审计 / 快照 / 部署 / dashboard） |
bash install.sh 装到 ~/.sofagent/bin/ |
| Dashboard | Web 驾驶舱（工作明细 / 图谱 / 健康） | sofagent web 起本地服务，读 data/ 运行时数据 |
🔌 DSH（DeepSeek Harness）生态
一句话定位：sofagent = FDE Harness 层，DSH = 执行宿主——sofagent 把 FDE 能力装进 DSH（及其他成熟 Agent），对执行体约束、对智力源治理，两者合一即完整 FDE Harness。四环节链路：
一、bash install.sh 装底座——MCP 自动配置随 --platform 落地（workbuddy/claude/cursor 写 mcp.json、codex 写 config.toml），装完即连
二、DSH 用户按需挂插件——skillhub install cordis-plugin-sofagent-<名>（SkillHub 通道，每款独立安装渐进采用）
三、plugin 经 @public API 调 sofagent 约束层（桥接实况见 AGENTS.md「DSH 插件家族」表）
四、审计 / 回滚走 MCP 工具面（run_audit / snapshot_restore 等）
📜 核心契约（不可违反）
📜 全文 SSOT：
core-rules.md（~30 行始终注入）——4 底线与 9 则铁律全文见该文件。岗位规范按 task type 按需加载（rules/role-*.md）。
4 底线
- 不泄露隐私
- 不执行危险操作
- 不生成有害内容
- 不冒充人类
9 则铁律
- 知行合一
- 目标驱动
- 全局视角
- 成本意识
- 存疑即问
- 不藏错误
- 有始有终
- 规范先行
- 勿增实体
品牌前缀铁律
向用户展示的审计结果必须保留 [sofagent] 前缀——去掉前缀，「审计验证」就退化成「模型自评」。不展示审计结果 = 没审计。展示格式见 skills/04-deliver.md，机制化细节见 rules/core-rules.md。
渐进式加载
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 11 KB
- agents/audit/SKILL.md 3.5 KB
- agents/engineer/SKILL.md 13 KB
- agents/fde/SKILL.md 6.7 KB
- agents/reviewer/SKILL.md 12 KB
- custom/README.md 5.6 KB
- harness/engage-fde.md 3.6 KB
- harness/engage.md 3.8 KB
- harness/entry-gate.md 4.9 KB
- harness/fde-template.md 4.9 KB
- harness/installer.md 6.3 KB
- harness/knowledge-maintain.md 2.5 KB
- harness/loop-check.md 4.9 KB
- harness/loop-evaluate.md 5.5 KB
- harness/loop-exit.md 2.7 KB
- harness/task-aware.md 5.2 KB
- harness/task-closure.md 2.7 KB
- rules/core-rules.md 1.5 KB
- rules/role-audit.md 1.2 KB
- rules/role-fde.md 1.2 KB
- rules/role-orchestrate.md 1.3 KB
- skills/01-entry.md 3.6 KB
- skills/02-discovery.md 7.1 KB
- skills/03-quantify.md 4.4 KB
- skills/04-deliver.md 4.8 KB
- skills/05-exit.md 4.0 KB
- state-machine-design.md 4.3 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 6b8b82d8559b
- 4d ago Changed 337b9b55f794
- 7d ago Changed 2f13c7d31253
- 8d ago Changed · +2 lines 19412e578ee8
- 12d ago Changed · -2 lines e2c849c13c35
- 15d ago Changed · +1 lines 8a2cc61be093
- 17d ago Changed · -5 lines 62904e2ba329
- 20d ago Changed · -1 lines 680cf6b11efe
- 22d ago Changed bdf314f0e768
- 24d ago First seen · 201 lines · 112 tokens per session scan A abd08d683913
sofagent is a skill published in the GitHub repository KongFangXun/sofagent (53 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 3,843 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skills
Instructions for using an agent that guides an enterprise AI project through discovery, assessment, architecture, prototype, and handoff stages. The process produces files and other structured deliverables, with analysis supplied by the host agent.
agent-guardrails
Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.
pinme-email
Use this skill when a PinMe project (Worker TypeScript) needs to integrate email sending (sendemail). Guides AI to generate correct Worker TS code.
design-impeccable
Anti-pattern detector and design rules for AI coding agents. Catches the specific mistakes AI makes when generating UI: gray text on color, nested cards, broken buttons, missing states. Use before shipping any frontend.
js-library-packaging
Use when a JavaScript/TypeScript package is consumed by another package — exports map, peer vs. direct dependencies, files allow-list, and whether it should be built at all.
stripe-spend
Create real Stripe test-mode charges for bounded business actions, with an authority-band budget cap and human escalation above the cap.