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 rules/fancy1108/clutch/cli-whitelist-docsgit clone --depth 1 https://github.com/fancy1108/ClutchWhat 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 | $0.00000 | $0.00724 |
| Opus 5 | $0.00000 | $0.00362 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
cli-whitelist-docs 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
Layer 4 操作剧本 · 不扩权。铁律见
CLAUDE.md；决策见memory/DECISIONS.mdD19。 本文件不定义新规则，仅描述「新增 Agent CLI 白名单」时的代码与文档同步步骤。
Agent CLI 白名单 — 代码 + 文档同步
用户要求「加 CLI」或你修改 CLI 白名单/路由时，同一 Task 内完成代码与文档，不单改代码。
代码（最小集）
| 文件 | 改动 |
|---|---|
services/orchestrator/src/tools_status.py |
CLI_CANDIDATES；若推荐则 RECOMMENDED_CLI_IDS |
services/orchestrator/src/engine_router.py |
CLI_ROUTING_CONFIGS curated 路由 |
services/orchestrator/src/agent_type.py |
AGENT_TYPES + 别名 |
services/orchestrator/src/provider_registry.py |
ProviderSpec（若一等公民路由） |
services/orchestrator/src/adapters/cli_adapter.py |
_CLI_BINARY_LABELS |
services/orchestrator/src/agent_executor.py |
tool id 集合 |
apps/desktop/src/services/cliInstallGuides.ts |
安装指引 + RECOMMENDED_CLI_IDS |
apps/desktop/src/services/agentTypes.ts |
显示名与 legacy 映射 |
apps/desktop/src/services/workflowAgentSteps.ts |
TOOL_LABELS |
services/orchestrator/tests/test_tools_status.py |
候选与 resolve_agent_type_for_tool |
文档（D19 必更）
docs/PRODUCT_INTRO.md— EngineRouter 列表、Tool Settings 推荐 CLIdocs/GETTING_STARTED.md— 中英「常见配置」表各一行CHANGELOG.md— 当前开发版本节 Added（现为## [1.4.0] - Unreleased，D59）README.md/README.zh-CN.md— CLI 能力表；若用--dangerously-skip-permissions则安全节memory/FILEMAP.md— 仅当路径映射有变docs/index.html— 官网引擎条带 + hero 浮层 logo（docs/assets/tool-logos/）apps/desktop/src/assets/tool-logos/+services/brandLogos.ts（若已路由）docs/research/pty-session.md— 附录引擎一览（可选，保持与路由一致）
示例：codebuddy-cli
- 二进制：
codebuddy（别名cbc） - 路由：
codebuddy -p+--dangerously-skip-permissions，conversation_mode: separate - 推荐列表首位（当前策略）
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 · 45 lines · 0 tokens per session scan A 361996034a13
cli-whitelist-docs is a cursor rule published in the GitHub repository fancy1108/Clutch (87 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 724 tokens. 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
core-project-context
Canonical project context and ownership rules.
documentation-sync
Mandatory documentation and feature checklist synchronization.
jelou-integration
Jelou webhook and WhatsApp messaging constraints.
backend-python
Python and FastAPI standards for the backend.
dashboard-typescript
React and TypeScript standards for the operator dashboard.
supabase-safety
Supabase migration, RLS and data security constraints.