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.
git clone --depth 1 https://github.com/oschina/mcp-giteeWrote 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/rules/oschina/mcp-gitee/mcp-gitee-schema)<a href="https://agentmods.dev/rules/oschina/mcp-gitee/mcp-gitee-schema"><img src="https://agentmods.dev/badge/rules/oschina/mcp-gitee/mcp-gitee-schema/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/rules/oschina/mcp-gitee/mcp-gitee-schema"><img src="https://agentmods.dev/badge/rules/oschina/mcp-gitee/mcp-gitee-schema.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 | $0.00919 | $0.00919 |
| Opus 5 | $0.00460 | $0.00460 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
mcp-gitee-schema 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 9d 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
MCP-Gitee Cursor Rule
1. 工具选择与基本规则
- 用户可通过工具名称（如 list_user_repos、create_issue、create_pull 等）选择所需操作。
- 每个工具均有简要描述，帮助用户理解其用途。
- 工具参数分为必填和可选，必填项未填写时禁止提交，可选项未填写时自动采用默认值。
- 参数类型、可选值、默认值均由系统自动校验和提示。
2. 参数填写与校验
- 所有参数均有类型校验（如数字、字符串、布尔值）。
- 枚举参数（如 visibility、state 等）仅允许选择指定范围内的值。
- project_id、program_id、assignee_id 等 ID 参数必须为数字，禁止填写名称或别名。
- 若参数为 ID 且用户不清楚，可先通过相关工具（如 search_users、list_user_repos）查询获取。
3. 工具组合与典型流程
3.1 仓库/项目管理
- 查询我的仓库：使用 list_user_repos，支持按 affiliation、type、visibility 等筛选。
- 查看仓库文件：选中仓库后，使用 get_file_content 查看 README 或其他文件。
- 在仓库下创建 Issue/Pull Request：结合 create_issue 或 create_pull 工具。
3.2 工作项流转
- 查找项目下工作项：先用 list_user_repos 找到仓库，再用 list_repo_issues。
- 筛选我负责的工作项：list_repo_issues 填写 assignee_id（数字）。
- 更新/评论工作项：选中 Issue 后，使用 update_issue 或 create_comment。
3.3 协作与代码合并
- 发起 Pull Request：list_user_repos 找到仓库，create_pull 填写分支、assignees 等。
- 查看/评论 Pull Request：list_repo_pulls 查看，list_comments 或 create_comment 参与讨论。
- 合并 Pull Request：merge_pull 工具。
3.4 版本发布
- 查看 Release：list_releases。
- 创建 Release：create_release，填写版本号、描述、目标分支等。
4. 工具间参数传递
- 工具输出的仓库名、用户ID、项目ID等可直接作为下一个工具的输入。
- 复杂操作建议分步进行，每步均可利用工具的筛选、查询和补全能力。
5. 智能提示与交互
- 系统自动提示参数类型、可选值、必填项。
- 参数填写错误时，系统给出明确提示并指导修正。
- 支持下拉选择、自动补全，减少手动输入错误。
- 不确定参数含义时，可查看工具描述或帮助文档。
6. 典型操作流程示例
示例1：新建 Issue 并指派同事
- list_user_repos 查询仓库
- search_users 查询同事ID
- create_issue 填写 owner、repo、title、assignee（同事ID）、program（项目ID，数字）
示例2：查找并处理我负责的工作项
- list_user_repos 查询仓库
- list_repo_issues 填写 assignee_id（你的ID）
- update_issue 或 create_comment 处理任务
示例3：发起代码合并并通知评审
- list_user_repos 查询仓库
- create_pull 发起 PR，填写 assignees
- create_comment 留言提醒评审
示例3：实现 Issue 并创建 Pull Request
- 获取 Issue 详情：get_repo_issue_detail
- 获取 Issue 评论：list_comments 填写 resource_type=issue
- 新建分支
- 实现 Issue
- 推送至远端 && 创建 Pull Request：create_pull
本规则适用于所有 MCP-Gitee 工具的终端用户，旨在提升操作效率、减少出错，支持多工具组合与参数智能传递。
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.
- 9d ago First seen · 89 lines · 919 tokens per session scan A 75a78164b7fe
mcp-gitee-schema is a cursor rule published in the GitHub repository oschina/mcp-gitee (65 stars, last pushed 2d ago), licensed MIT. It adds 919 tokens to every session, about $0.0046 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 cursor rules, from other repositories
windsurfrules
Pare wraps CLI tools in MCP servers returning structured JSON. Always prefer Pare MCP tools over raw CLI.
conventional-commits
Enforce Conventional Commits format for all commit messages.
git-workflow
Branch hygiene — rebase on main before every PR and keep branches synced.
commit-pattern
Conventional Commits, message format, and pre-commit analysis (local hook + checks).
development-workflow
Cursor rule "development-workflow" from floriscornel/todo-mcp, covering development workflow for todo mcp, testing & quality assurance, commit structure, branch & pr workflow and publication & releases.
manage-scope-iteratively
Implement features incrementally with checkpoints; don't code for 2 hours then show work.