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/skill-changegit 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 | $0.01505 |
| Opus 5 | $0.00000 | $0.00753 |
| Sonnet 5 | $0.00000 | $0.00301 |
| Haiku 4.5 | $0.00000 | $0.00151 |
Grade A, and why
skill-change 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 yesterday.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 文案 / 路由 / 安装约定
触发条件
- 改
skills/*/SKILL.md的 description、路由表、consent、安全闸、hand-off、references 落款 - 调整
bailian-protocol与业务 skill 的关系，或业务 skill 之间的软 hand-off 约定 - 新增 / 拆分 / 合并
bailian-*业务 skill，或改tools/generate-reference.ts的GROUP_OWNER_SKILL归属（与命令增删改交叉时两边都看） - 给业务 skill 补安装说明、README，或统一「勿猜 flag →
reference/」类约定
纯改生成物 skills/*/reference/*.md（由命令 metadata 驱动）→ 走 command-add-remove.md / command-flag-change.md，不要手改 reference。
统一口径（安装）
- Supported install：
bl skill init（装齐 registry 中全部bailian-*，含bailian-protocol） bailian-protocol是共享协议 skill，业务 skill 执行前应 Read 它- 不要在 frontmatter 写
companions，也不要对外说「companions = 安装器硬依赖」 - 子集安装：
bl skill add --name bailian-protocol,<skill>；漏装 protocol 会导致相对路径 Read 失败 bl skill add --all： 安装 registry 全量（含spark-video等非 bailian 技能）；一键安装 /bl update用skill init，不要用--all
概念图
bailian-protocol ← 共享协议（consent / 鉴权 / 版本 / 错误上报）
▲ 靠 `bl skill init` 与业务 skill 同装；非安装器强制 companions
│
┌───────┴────────┬────────────────┬──────────────────┬───────────────────┐
bailian-gen bailian-finetune bailian-managed-agent bailian-web-search
（领域路由表） （领域工作流） （IaC 安全闸） （搜索路由+兜底）
│ │ │ │
└────────────────┼──────────────────┴─────────────────────┘
▼ 软 hand-off（按 skill 名）
bailian-cli（hub）
hub 路由表：本职命令 + 领域 hand-off 行
细节 → 各 skill reference/（生成）
必查清单
A. 分层边界
- 整包装齐：安装/升级文案主推
bl skill init；业务 skill 不声明companions - 协议读取：CRITICAL / references 可链
../bailian-protocol/…；若读不到 → 停止执行bl，提示bl skill init - 软 hand-off：兄弟业务 skill 只写 skill 名；已安装则 Read，未安装则
bl … --help或提示整包安装；不要把../bailian-gen/…等写成执行前提 - Hub vs 领域：
bailian-cli的「When to use which command」只列 hub 拥有的意图；媒体 / 精调 / managed-agent 各留 hand-off 行，不抄领域默认模型与子命令明细 - 渐进披露：SKILL 写意图路由与领域硬规则；flags / usage / examples 以
reference/或bl <command> --help为准，表后保留「勿猜 flag」指向句
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.
- yesterday First seen · 78 lines · 0 tokens per session scan A ec061e05ce7c
skill-change 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 1,505 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.