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/dsh-plugingit 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 | $0.02612 |
| Opus 5 | $0.00000 | $0.01306 |
| Sonnet 5 | $0.00000 | $0.00522 |
| Haiku 4.5 | $0.00000 | $0.00261 |
Grade A, and why
dsh-plugin 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dsh 插件维护（packages/bailian-kb-dsh）
触发条件
- 改
packages/bailian-kb-dsh的工具（kb_search/kb_chat）、服务缓存、settings / 凭据解析 - 改 web 半（Settings 配置页 React 组件、CSS Modules）
- 升级
@deepseek-ai/dsh-*peer 依赖 - 改插件包名、bundle 声明或产物布局
- 发布插件到 npm
这个包和其他 packages 不一样的地方
它是下游宿主适配层：依赖方向朝外（消费 bl CLI 与百炼 API，装进 DeepSeek Harness 运行），不是 core → runtime → commands → 产品入口 这条链上的一环。由此带来四条与 packages/* 通行约定的故意偏离：
| 项 | 本包 | 其他包 | 原因 |
|---|---|---|---|
| 版本 | 独立 0.1.x |
core/runtime/commands/cli/kscli 锁步 | 跟随 dsh 的 rc 节奏，与 bl 发版无关；不在 tools/release/lib/packages.mjs 白名单里 |
| 构建 | tsc + tsdown |
vp pack |
浏览器半需要 __ModuleLoader__ banner/footer 与 lightningcss CSS Modules 内联，vp pack 产不出 |
| 发布 | publish.yml 里 package=bailian-kb-dsh job，走 publish-kb-dsh.mjs |
publish.yml 里 publish-stable/channel.mjs |
不在 bailian-cli 依赖闭包内，版本与构建都不同，不能与 bl 共用同一条 script |
| tsconfig | 三个 | 一个 | 见下 |
tsconfig 三件套（改动前先读）
| 文件 | 谁在用 | 作用 |
|---|---|---|
tsconfig.json |
oxlint / vp check 自动发现 |
纯类型检查，覆盖 src + tests 两半：noEmit + jsx: react-jsx + DOM lib + allowImportingTsExtensions |
tsconfig.build.json |
build script（tsc -b） |
产出 node 半到 dist/，exclude: src/web |
tsconfig.web.json |
build / typecheck script |
web 半的隔离检查：types: []，确保浏览器代码不误用 node 全局 |
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 · 126 lines · 0 tokens per session scan A 4aed4c9a5124
dsh-plugin 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 2,612 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.