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 agentmods add skills/kongfangxun/sofagent/cordis-plugin-sofagent-auditnpx skills add KongFangXun/sofagent --skill cordis-plugin-sofagent-auditgit 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/cordis-plugin-sofagent-audit)<a href="https://agentmods.dev/skills/kongfangxun/sofagent/cordis-plugin-sofagent-audit"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/cordis-plugin-sofagent-audit.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.00329 |
| Opus 5 | $0.00053 | $0.00164 |
| Sonnet 5 | $0.00021 | $0.00066 |
| Haiku 4.5 | $0.00011 | $0.00033 |
Grade A, and why
cordis-plugin-sofagent-audit 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 4d 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.
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.
What it actually says
cordis-plugin-sofagent-audit
变更机器审阅——24 规则 + git diff 硬证据 + 节点级审计（seam: tools/result + tools/pre-execute + fs/write-intent）——桥接 @sofagent/audit runRules（sofagent 品牌插件 · 主色 #16B8F3）
用途
本插件随 sofagent 主线版本发布（SkillHub 通道：skillhub install cordis-plugin-sofagent-audit 安装与检索；npm 通道未开通）。版本号与 sofagent 主线对齐。
相关链接
- sofagent 主仓：https://github.com/KongFangXun/sofagent
- 开发日志：docs/changelog/v1.4/v1.4.0.md（DSH 插件家族）
What ships with it
5 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.
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.
- 4d ago First seen · 23 lines · 105 tokens per session scan A b0ce33054c8e
cordis-plugin-sofagent-audit is a skill published in the GitHub repository KongFangXun/sofagent (41 stars, last pushed 6d ago), licensed MIT. It adds 105 tokens to every session and 329 once invoked, about $0.0005 per session on Opus 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
execution
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。.
review
M-1.5 review skill — 在 patch 跟 contract 之间找 finding，produce Finding 一等对象。.
fix-self-check
M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。.
plan-decompose
从 completioncondition + conceptgraph 递归分解出 primitive task 提案。主 planner session 决定接受/调整/拆得更细。.
agent-workflow-playbook
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…
dependency-analyze
从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集；已有预判逐条标「待复核」交它取证。.