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 skills/echovic/blade-code/lsp-code-intelligencenpx skills add echoVic/blade-code --skill lsp-code-intelligencegit clone --depth 1 https://github.com/echoVic/blade-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/echovic/blade-code/lsp-code-intelligence)<a href="https://agentmods.dev/skills/echovic/blade-code/lsp-code-intelligence"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/lsp-code-intelligence.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00161 | $0.02653 |
| Opus 5 | $0.00081 | $0.01326 |
| Sonnet 5 | $0.00032 | $0.00531 |
| Haiku 4.5 | $0.00016 | $0.00265 |
Grade A, and why
knowledge-extension-ecosystem-lsp-code-intelligence 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- knowledge-tool-contracts-and-registry — 86% identical, 152 lines differ
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Structure
LSP 配置按 source project 解析并冻结,SessionRuntime 再以 execution workspace
创建私有 manager;语言服务器按目标文件扩展名懒启动,语义查询和写后诊断共享同一连接。
Directory Layout
packages/cli/src/lsp/— LSP client、Session manager 与 Workspace 资源快照packages/cli/src/config/lspSettings.ts— LSP server 配置规范化和硬边界packages/cli/src/tools/builtin/lsp/— ReadOnly LSP 工具与协议结果格式化packages/cli/src/ide/— IDE 检测和 Blade IDE 扩展安装入口docs/reference/lsp-session-intelligence.md— Session LSP 行为契约与资格要求
Key Entry Points
resolveWorkspaceLspResources()inpackages/cli/src/lsp/WorkspaceLspResources.ts— 合并用户、项目和插件服务器并冻结快照LspSessionManager.query()inpackages/cli/src/lsp/LspSessionManager.ts— 执行语义查询LspSessionManager.afterToolUse()inpackages/cli/src/lsp/LspSessionManager.ts— 写后同步并回注新诊断LspClient.start()/LspClient.stop()inpackages/cli/src/lsp/LspClient.ts— 管理 stdio JSON-RPC 与 owned process treecreateLspTool()inpackages/cli/src/tools/builtin/lsp/lsp.ts— 将 manager 暴露为统一只读工具
API Surface
Workspace LSP Resources
resolveWorkspaceLspResources(projectRoot, base)— 合并 Workspace 配置和插件.lsp.jsonsnapshotWorkspaceLspResources(resources)— 规范化、深拷贝并冻结 Session 配置
LspSessionManager
available— 仅在存在启用服务器、Session 非 ACP remote 且未 dispose 时为真query(input, signal)— 路由 definition、references、hover、symbols、implementation、call hierarchy 或 diagnosticsafterToolUse(toolName, params, result, context)— 同步成功写操作并把新诊断追加到 ToolResultgetStatus()— 返回服务器状态、重启次数、扩展映射和最近错误dispose()— 解除 waiter、发送 shutdown/exit 并回收所有服务器进程
LspClient
start(options)/initialize(params, timeout, signal)— 建立 stdio transport 与协议握手request(method, params, timeout, signal)— 带 JSON-RPC cancellation 和本地 timeout 的请求stop(timeout)— 尝试协议关闭后以 owned process tree 作为最终回收边界
Usage Examples
Session 创建私有 Manager (packages/cli/src/agent/runtime/SessionRuntime.ts)
this.lspManager = new LspSessionManager({
sessionId: this.sessionId,
workspaceRoot: this.workspaceRoot,
environment: this.sessionEnvironment,
servers: this.lspResources.servers,
});
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 · 114 lines · 161 tokens per session scan A fc80b8c1ef77
knowledge-extension-ecosystem-lsp-code-intelligence is a skill published in the GitHub repository echoVic/blade-code (178 stars, last pushed today), licensed MIT. It adds 161 tokens to every session and 2,653 once invoked, about $0.0008 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
tricorder-cli
Full CLI reference for the tricorder daemon (build diagnostics, test results, source lookup, eval comments, logs). This is the fallback invoked by the tricorder skill when the tricorder-mcp MCP tools aren't available or aren't working — invoke tricorder first; it decides whether this is needed.
tricorder-mcp
Check GHCi build status, diagnostics, and test results for this Haskell project via the tricorder MCP server. Use when asked to check the build, see compiler errors/warnings, or run tricorder.
tricorder
Check GHCi build status, compiler errors/warnings, or test results for this Haskell project. Use when asked to check the build, see errors/warnings, or run tricorder.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.