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/tddh/clum/agents-mdgit clone --depth 1 https://github.com/tddh/clumWhat 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 | $0.00849 | $0.00849 |
| Opus 5 | $0.00425 | $0.00425 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
clum 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 2d 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
clum 项目开发规则
MCP 工具使用规则(最高优先级)
以下规则优先级最高,必须严格遵守:
-
默认会话:所有 clum 操作必须使用
session_name="clum",除非用户明确指定其他会话名 -
默认 Pane:
pane_id可省略,server 自动选择 window 0 中编号最小的 pane。破坏性工具(close_pane、paste_buffer、respawn_pane)必须显式指定 -
禁止随意创建会话:不要自作主张创建
test-session、debug-session等新会话,除非用户明确要求 -
先 attach 后 create:操作前先
session_attach检查会话是否存在,不存在才session_create -
保留会话:执行完命令后,不要主动清理 session(禁止调用
kill_session、close_window、close_pane),除非用户明确要求"清理"、"关闭"、"销毁" -
以用户指令为主:用户的明确指令优先于以上所有默认规则。如果用户指令信息不明确(如未指定主机、会话名、操作目标等),必须先向用户确认再执行,禁止猜测或自作主张
-
开发/测试隔离:在 clum 项目自身开发调试期间,若需在远程主机上执行测试命令(如重启 bridge、修改配置、编译验证等),必须创建独立的临时会话(如
session_name="dev"),严禁占用clum默认会话。测试完成后清理该会话(kill_session)。严禁对clum默认会话执行exit、kill_session、close_pane、close_window等破坏性操作——即使用户明确指示了相关操作,也必须先确认目标是否为clum会话,若是则拒绝执行并说明原因。
违反这些规则 = BUG,没有例外。
开发规范
- Rust 代码必须通过
cargo clippy --workspace -- -D warnings无警告 - 提交前运行
just check确保编译通过 - 遵循现有代码风格和命名规范
- 新功能必须添加对应的测试
- 文档更新与代码变更同步
项目结构
clum/
├── crates/ # Rust crates
│ ├── clum-cli/ # CLI 交互式终端
│ ├── clum-core/ # 共享类型(HostConfig, AuditEvent, AuditAction)
│ ├── clum-mcp/ # MCP Server(Central Server 模式 / stdio 本地模式)
│ └── rmux-bridge/ # Bridge proxy
├── config/ # 配置文件
├── docs/ # 文档
├── deploy/ # 部署脚本(install.sh, deploy-bridge.sh, deploy-mcp.sh)
├── scripts/ # 迁移与测试脚本(migrate-to-clum.sh, mcp_smoke.py)
├── .opencode/skills/ # AI 开发辅助 Skills (OpenCode)
└── .qoder/skills/ # AI 开发辅助 Skills (Qoder)
常用命令
just check # cargo check --workspace
just test # cargo test --workspace
just fmt # cargo fmt --all
just lint # cargo clippy --workspace -- -D warnings
just build # cargo build --workspace
just release-linux # 交叉编译 Linux x86_64
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.
- 2d ago First seen · 53 lines · 849 tokens per session scan A dd975e6c6a66
clum AGENTS.md is an instructions file published in the GitHub repository tddh/clum (5 stars, last pushed 5d ago), licensed MIT. It adds 849 tokens to every session, about $0.0042 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
cmuxlayer AGENTS.md
Instructions for EtanHey/cmuxlayer, covering cmuxlayer, what this repo is for, the one principle, resumable, automatically and the tools are the product.
cmuxlayer CLAUDE.md
Instructions for EtanHey/cmuxlayer, a project described as: 10 public MCP tools for controlling cmux workspaces and managing Claude, Codex, Gemini, Kiro, and Cursor agents.
aiops-mcp AGENTS.md
AGENTS.md instructions for rmednitzer/aiops-mcp, covering agents.md, one-line, repo map, hard rules and build and test.
ssh-mcp-pro AGENTS.md
AGENTS.md instructions for oaslananka/ssh-mcp-pro, covering agents.md - ssh-mcp-pro, quick start, secure defaults, recommended workflow and explain mode.
coolify-mcp CLAUDE.md
Claude Code instructions for jurislm/coolify-mcp, covering claude.md, project overview, commands, run locally and architecture.
coolify-mcp copilot-instructions.md
Copilot instructions for jurislm/coolify-mcp, covering copilot instructions for coolify-mcp, project overview, git workflow, version numbers and build & test.