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/url-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 | $0.01015 |
| Opus 5 | $0.00000 | $0.00508 |
| Sonnet 5 | $0.00000 | $0.00203 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
url-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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
URL / 渠道变更
触发条件
- 控制台域名变更(如
bailian.console.aliyun.com→ 新域名) - API endpoint 迁移
- 文档站迁移
- 调整 / 删除 / 新增渠道追踪参数(
source_channel等)
URL 的分层架构
core/config/schema.ts ← API endpoint / 文档站(region-aware)
REGIONS{cn, us, intl} dashscope.aliyuncs.com 等
DOCS_HOSTS{cn, us, intl} help.aliyun.com/zh/model-studio
BAILIAN_HOST bailian.cn-beijing.aliyuncs.com (OpenAPI)
runtime/src/urls.ts ← 用户面控制台 URL(cn-only)
BAILIAN_CONSOLE_ROOT bailian.console.aliyun.com
BAILIAN_CONSOLE BAILIAN_CONSOLE_ROOT/cn-beijing
API_KEY_PAGE BAILIAN_CONSOLE/?tab=app#/api-key
TOKEN_PLAN_PAGE BAILIAN_CONSOLE_ROOT/cn-beijing?tab=plan#/efm/subscription/overview
MCP_WEBSEARCH_PAGE mcpMarketplaceDetailPage("WebSearch")
mcpMarketplaceDetailPage BAILIAN_CONSOLE?tab=mcp#/mcp-market/detail/<serverCode>
core/files/upload.ts ← 文件上传 endpoint(cn-pinned)
UPLOAD_API ${REGIONS.cn}/api/v1/uploads
必查清单
A. TS 源码(必须 import,不准硬编码)
-
packages/core/src/config/schema.ts是所有 API/docs 基址的源头 -
packages/runtime/src/urls.ts是所有用户面控制台 URL 的源头 - 改完后 grep 验证:
# 控制台 URL — 应只在 urls.ts 出现
grep -rnE "https://bailian\.console\.aliyun\.com" packages/ --include="*.ts" \
| grep -v "node_modules" | grep -v "/dist/"
# 期望:匹配 packages/runtime/src/urls.ts;
# 当前遗留例外:packages/commands/src/commands/auth/login-console.ts(登录站点映射)、
# packages/core/src/advisor/recommend.ts(模型文档 deep link)。触碰时优先收敛到统一 URL 模块。
# API endpoint — 应只在 schema.ts 和 upload.ts 出现
grep -rnE "https://dashscope[a-z-]*\.aliyuncs\.com" packages/ --include="*.ts" \
| grep -v "node_modules" | grep -v "/dist/"
# 期望:只匹配 schema.ts(REGIONS)、upload.ts(派生)、tests
B. 非 TS 文件(只能人工同步,无法 import)
-
skills/*/reference/各<group>.md中 API/控制台 URL(generate:reference重建后核对并提交) -
README.md/README.zh.md中所有 URL
C. 渠道追踪参数
- 当前现状:TS 源码不带
source_channel=...;README / package README 中保留cli_github/key_github等用户入口追踪参数 - 如未来调整追踪参数,统一评估 README、
packages/cli/README*、packages/core/README*与 package homepage,不要单点改造成不一致 - grep
source_channel=,确认每个残留都属于预期用户面文档或已批准的追踪入口
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 · 80 lines · 0 tokens per session scan A 9e4310116742
url-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 1,015 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.