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/build-release-and-documentationnpx skills add echoVic/blade-code --skill build-release-and-documentationgit 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/build-release-and-documentation)<a href="https://agentmods.dev/skills/echovic/blade-code/build-release-and-documentation"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/build-release-and-documentation.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 | $0.00182 | $0.02919 |
| Opus 5 | $0.00091 | $0.01460 |
| Sonnet 5 | $0.00036 | $0.00584 |
| Haiku 4.5 | $0.00018 | $0.00292 |
Grade A, and why
knowledge-engineering-quality-and-delivery-build-release-and-documentation 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Structure
交付链以 packages/cli/package.json 为 npm 权威版本，先把 Node CLI 与 Vite Web 构建到一个发布目录，再由版本 tag 触发 OIDC npm 发布；文档站从 Git 可见双语源和部署时生成的 changelog 组成。
Directory Layout
package.json— 私有 monorepo 工作区和 CLI/VS Code 聚合命令packages/cli/package.json—blade-code发布版本、bin、files、依赖和 prepackpackages/cli/scripts/build.ts、packages/cli/web/vite.config.ts— 后端 ESM 与 Web 静态资源构建packages/vscode/package.json— 独立 VS Code 扩展构建，不进入blade-codenpm 文件清单packages/cli/scripts/release.js、packages/cli/release.config.js— 本地版本、changelog、tag 与 push 编排scripts/release.sh、scripts/setup-auto-release.sh、scripts/get-npm-token.sh— 仓库遗留发布辅助脚本.github/workflows/ci.yml、.github/workflows/publish.yml、.github/workflows/docs.yml— CI、npm/GitHub Release 与 PagesCHANGELOG.md、CHANGELOG.zh.md、docs/— 英文权威 changelog、中文同步记录和双语 Docsify 源vendor/ripgrep/、packages/cli/vendor/ripgrep/— 可选二进制的忽略目录与 Git 可见说明
Key Entry Points
packages/cli/scripts/build.ts— 清空dist、externalize 运行时依赖、构建 CLI 并调用 Vitepackages/cli/scripts/release.js— 本地版本递增、changelog、构建、提交、tag 和 pushpackages/cli/release.config.js— 决定本地发布脚本实际跳过或执行哪些步骤.github/workflows/publish.yml— tag 或手动 dispatch 的幂等 npm/GitHub Release.github/workflows/docs.yml— changelog 复制和 GitHub Pages 部署AGENTS.md— 当前仓库要求的独立 patch、双语 changelog 和发布前验证契约
Branching Table
| 维度 | 分支 A | 分支 B |
|---|---|---|
| 根构建目标 | build:cli 构建可发布 CLI 与嵌入 Web |
build:vscode 独立输出 VS Code extension |
| CLI 构建内容 | Bun 将 src/blade.tsx 打成 Node ESM chunks，依赖保持 external |
Vite 将 Web 打到 packages/cli/dist/web 并按 React/xterm/radix/session-events 分块 |
| 开发与发布 | 开发从源码 watch 启动 | npm 只暴露 dist/blade.js，并依赖 prepack 重新构建 |
| 本地发布与远端发布 | release.js 递增版本、生成英文 changelog、提交并推 tag |
publish.yml 校验 tag=包版本后构建并通过 OIDC 发布 |
| workflow 入口 | tag push 检出触发 tag | 手动 dispatch 检出调用者指定的既有 tag |
| npm 状态 | 版本不存在时执行 npm publish --access public |
版本已存在时跳过 publish，继续确保 GitHub Release |
| 文档 changelog | 根 CHANGELOG.zh.md/CHANGELOG.md 是维护源 |
部署时复制到被忽略的 docs/changelog.md/docs/en/changelog.md |
| 浏览器与搜索资产 | Playwright 包和可选 @vscode/ripgrep 随 npm 依赖解析 |
Chromium 与 vendored ripgrep 二进制都不是普通源码 checkout 自动具备的资产 |
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 · 98 lines · 182 tokens per session scan A ac4c002f2786
knowledge-engineering-quality-and-delivery-build-release-and-documentation is a skill published in the GitHub repository echoVic/blade-code (178 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 2,919 once invoked, about $0.0009 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
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
golang-continuous-integration
GitHub Actions CI/CD pipeline configuration for Golang projects — workflow files for test, lint, SAST, coverage and vulnerability-scan jobs, Dependabot and Renovate config files, GoReleaser release pipelines, Docker build/push, repository security settings, and AI-driven PR review. Use when setting up or improving Go…
meta-long-running-build-watchdog
Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
deploy
Deploy the application or manage infrastructure. Handles Docker builds, CI/CD, and deployment workflows.
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.