Borrowing it
Nothing to install: this file belongs to KongFangXun/sofagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/KongFangXun/sofagent/main/AGENTS.mdgit 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/instructions/kongfangxun/sofagent/agents-md)<a href="https://agentmods.dev/instructions/kongfangxun/sofagent/agents-md"><img src="https://agentmods.dev/badge/instructions/kongfangxun/sofagent/agents-md/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/instructions/kongfangxun/sofagent/agents-md"><img src="https://agentmods.dev/badge/instructions/kongfangxun/sofagent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00566 | $0.00566 |
| Opus 5.5 | $0.00226 | $0.00226 |
| Sonnet 5.5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade B, and why
sofagent AGENTS.md scanned grade B with 1 finding 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 27d ago.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# ~/.codex/config.toml What it actually says
AGENTS.md · sofagent Codex 适配（薄挂载）
本文件是 Codex CLI 的顶层指令挂载点（AGENTS.md 约定），不含规范内容——四层加载链的规范资产唯一来源是 sofagent 的
SKILL/目录（单一真相源）。规则更新只发生在 SKILL/，本文件永不复制它们。区分：
FORGE/SKILL/不是规范资产——它仅存放 FORGE 内部循环（fresh-eyes-loop、release-gate-loop）的技能定义，与根SKILL/规范目录同名但职责无关。
会话开始时按序加载（四层加载链）
一、读取已安装的 SKILL.md 作为系统约束（L1 硬约束）：
~/.sofagent/skills/sofagent/SKILL.md
（若用 bash install.sh --platform codex 安装，fde.md 已写入 ~/.codex/fde.md。）
二、读取用户工作规则（L2）：~/.codex/fde.md（或 ~/.sofagent/skills/sofagent/fde.md）
三、读取反思区（L3）：~/.sofagent/skills/sofagent/think.md
四、知识库（L4）：~/.sofagent/skills/sofagent/knowledge/ 目录，按任务关键词检索加载。
model_instructions_file（可选）
Codex 的 model_instructions_file 配置可直接指向 SKILL.md，让约束进系统层：
# ~/.codex/config.toml
model_instructions_file = "~/.sofagent/skills/sofagent/SKILL.md"
审计强制（平台无关）
约束是建议性的，审计是强制性的——提交前审计走 git hook（sofagent audit --install-hook），与宿主平台无关：28 条 git diff 规则 + HMAC 链审计在 Codex 下同样生效。
连接 MCP Server
104 个 tool（run_audit / worklog_query / snapshot_restore / fde_interview / connector_list 等）经 MCP 协议面暴露——适配器只依赖 @public API 子集，@internal 破坏性变更不影响本挂载。默认全量暴露，SOFAGENT_MCP_ROLES 显式收窄专职面。
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.
- 27d ago Changed 5d9c0e5f9f55
- 1mo ago Changed · -1 tokens per session 0047481dd4e2
- 1mo ago Changed 4d58e55767b3
- 1mo ago Changed 970a21d9f186
- 1mo ago Changed db138ba96f39
- 1mo ago Changed f47ff0893ef2
- 1mo ago Changed · +5 tokens per session 15b5a367b7da
- 1mo ago Changed b0e3d3ebdc98
- 1mo ago Changed 9d7d0139df11
- 2mo ago First seen · 39 lines · 562 tokens per session scan B 7e98970d6726
sofagent AGENTS.md is an instructions file published in the GitHub repository KongFangXun/sofagent (55 stars, last pushed yesterday), licensed MIT. It adds 566 tokens to every session, about $0.0023 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
sofagent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sofagent AGENTS.mdKongFangXun/sofagent | Instructions file | 55 | yesterday | MIT | B | 566 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |