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 instructions/zyx379/zoehis_workflow/agents-mdgit clone --depth 1 https://github.com/zyx379/zoehis_workflowWrote 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/zyx379/zoehis_workflow/agents-md)<a href="https://agentmods.dev/instructions/zyx379/zoehis_workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/zyx379/zoehis_workflow/agents-md.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 5.1 | $0.00938 | $0.00938 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
zoehis_workflow AGENTS.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fj-common — Agent 指引
福建通用 HIS 多仓库聚合工作区（10 个独立 Git 子仓库，根目录无 Git）。
开发（改代码）
- 每次需求按步骤执行： docs/workflow.md（最终版 + 开场模板）
- 遵守
dev/rules/zoehis-*.mdc（Cursor 经.cursor/rules联接加载；含 Step 8、系统参数规范zoehis-sys-param） - 使用 Skill zoehis-ai-dev（
dev/skills/，经.cursor/skills联接）；Step 4 代码地图用 zoehis-code-map - 配置说明：docs/ai-dev-setup-workflow.md
- 多设备同步：docs/multi-device-sync.md（GitHub 配置仓）
- 多编辑器协作：docs/multi-editor-cursor-collab.md（Trae/CodeBuddy → Cursor）
生产排查
| 场景 | 文档 |
|---|---|
| MCP / traceId 可达 | Skill dev/skills/his-log-diagnosis + MCP zoe-his-mcp（dev/mcp/zoe-his-mcp/，workflow 分支 A） |
| 现场库不可达 | docs/排查/现场离线排查流程.md（分支 B，只读代码逻辑分析，验证前不改代码） |
子仓库路径：所有后端代码均在本地子目录（如
onelink-micro-charge-fj-common/），排查时直接 Read/Grep，不要误判为"代码不在本地"。完整映射见 Skillzoehis-code-map。
Git 约定摘要
- 实现期：只改代码 + master pull，不提交
- 提交标题：
[禅道号/需求号]【项目名称】需求标题 - 禁止 commit 含
Co-authored-by: Cursor/[email protected]（见 Rulezoehis-git-branch） - 人审后：「审查通过，提交并 push」→ 各仓 push master
- 「审查通过，提交并发布」→ push master → 按 commit 关键词 merge（【漳州二院】→ release-1.166；【漳州市医院】→ release-1.168）→ 项目分支 tag 最大值 +1；无需再确认是否编译，直接回报 tag 号（CI 自动打包）
onelink-web-cis-common：push master 后，在 master 打release-1.0.{max+1}tag（默认 release-1.0 系列，不打医院 release-* 分支）；2026-07-13 用户明确覆盖旧「仅 push master」规则（曾误改 release-0.0，同日纠正）- 交付后 默认 Step 12 写
docs/memory/cases/（见 Skill zoehis-ai-dev）
测试造数
- Step 11（默认跳过）：MCP
zoe-his-mcp（dev/mcp/zoe-his-mcp/）在测试库 INSERT/UPDATE 造数 + SELECT 验证（见docs/workflow.md）
工作经验记忆库
- 长期：docs/memory/cases/ + index — 开发交付 Step 12 沉淀
- 短期：docs/memory/short-term/ — Step 4–5 分析/spec；交付后删除
- 排查类（分支 A/B）：召回见 workflow「排查类共用约定」；纯排查 不写 cases；可复用模式 →
his-log-diagnosis/cases.md
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.
- 5d ago First seen · 42 lines · 938 tokens per session scan A 8a38126ddab8
zoehis_workflow AGENTS.md is an instructions file published in the GitHub repository zyx379/zoehis_workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 938 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).