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 agents/modelstudioai/cli/command-add-removegit clone --depth 1 https://github.com/modelstudioai/cliWhat 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 | $0.02360 |
| Opus 5 | $0.00000 | $0.01180 |
| Sonnet 5 | $0.00000 | $0.00472 |
| Haiku 4.5 | $0.00000 | $0.00236 |
Grade A, and why
command-add-remove 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令增删改
触发条件
- 增加新的
bl xxx命令 - 删除已有命令
- 重命名命令(包括从单级
bl x改成bl x y或反向) - 调整某个 shared command 在
bl/kscli等产品入口里的暴露路径
命令实现与产品路径的关系
命令实现住在 packages/commands,产品路径由入口包决定。实现文件路径按能力组织,但不再等同于最终命令路径。
实现文件:
packages/commands/src/commands/knowledge/retrieve.ts
↓ packages/commands/src/index.ts export { default as knowledgeRetrieve }
产品入口:
packages/cli/src/commands.ts "knowledge retrieve": knowledgeRetrieve ↔ bl knowledge retrieve
packages/kscli/src/main.ts "retrieve": knowledgeRetrieve ↔ kscli retrieve
常见路径形态:
单级命令: packages/commands/src/commands/update.ts ↔ bl update
两级命令: packages/commands/src/commands/text/chat.ts ↔ bl text chat
子组命令: packages/commands/src/commands/memory/profile-get.ts ↔ bl memory profile get
子组要慎用:只有子组下有 ≥2 个 action 时才合理,否则优先拍平到两级。
CLI 命令注册架构(必读)
packages/commands 是命令库,只导出单个 command;不内置 path presets,不关心 bl / kscli。每个产品入口传入自己的 command map,runtime 负责解析、help、鉴权、遥测、执行。
packages/commands/src/commands/<...>.ts
defineCommand({ auth, flags, usageArgs, exampleArgs, validate, run })
↓
packages/commands/src/index.ts
export { default as xxxCommand } from "./commands/...ts"
↓
┌──────────────────────────────┬──────────────────────────────┐
│ packages/cli/src/commands.ts │ packages/kscli/src/main.ts │
│ { "text chat": textChat } │ { "retrieve": knowledge... } │
└──────────────┬───────────────┴──────────────┬───────────────┘
↓ ↓
createCli(commands, identity) → runtime registry/help/middleware
↓
tools/generate-reference.ts reads packages/cli/src/commands.ts
packages/commands/src/commands/<...>.ts:命令实现;usageArgs/exampleArgs只写参数片段,不写bl/kscli前缀packages/commands/src/index.ts:导出命令实现;新增命令必须在这里 re-exportpackages/cli/src/commands.ts:bl产品命令 map;新增/删除/重命名bl命令必须改这里packages/kscli/src/main.ts:kscli产品命令 map;只有该入口需要暴露/变更时才改packages/runtime/src/registry.ts:通用 registry,从传入 map 建树;不要在这里登记业务命令tools/generate-reference.ts:pre-commit /pnpm run sync:skill-assets时读packages/cli/src/commands.ts,按GROUP_OWNER_SKILL归属表分流写到各skills/<skill>/reference/index.md+<一级命令>.md。未显式归属的一级组默认进bailian-cli。各目录纳入 git,勿手改。新增一级命令组若应归领域 skill,记得改归属表。
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 · 138 lines · 0 tokens per session scan A c9bc153cd0f7
command-add-remove is an agent published in the GitHub repository modelstudioai/cli (320 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,360 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 agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.