Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Covers ToolExecutor 的验证、worktree 隔离、权限、Hook、审批、并发准入、文件锁、调用重试、LSP/AutoVerify 后处理与结果投影。
$ npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install echoVic/blade-code knowledge-tool-execution-pipeline --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline .claude/skills/knowledge-tool-execution-pipeline && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "knowledge-tool-execution-pipeline" agent skill from https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline into .claude/skills/knowledge-tool-execution-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-tool-execution-pipeline", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipelineType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install echoVic/blade-code knowledge-tool-execution-pipeline --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline .agents/skills/knowledge-tool-execution-pipeline && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "knowledge-tool-execution-pipeline" agent skill from https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline into .agents/skills/knowledge-tool-execution-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-tool-execution-pipeline", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install echoVic/blade-code knowledge-tool-execution-pipeline --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline .cursor/skills/knowledge-tool-execution-pipeline && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "knowledge-tool-execution-pipeline" agent skill from https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline into .cursor/skills/knowledge-tool-execution-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-tool-execution-pipeline", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/echoVic/blade-code.git --path .trae/knowledges/tool-and-automation-platform/tool-execution-pipeline--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install echoVic/blade-code knowledge-tool-execution-pipeline --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline .gemini/skills/knowledge-tool-execution-pipeline && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "knowledge-tool-execution-pipeline" agent skill from https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline into .gemini/skills/knowledge-tool-execution-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-tool-execution-pipeline", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install echoVic/blade-code knowledge-tool-execution-pipelineInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .github/skills && cp -r skills-src/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline .github/skills/knowledge-tool-execution-pipeline && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "knowledge-tool-execution-pipeline" agent skill from https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline into .github/skills/knowledge-tool-execution-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-tool-execution-pipeline", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install echoVic/blade-code knowledge-tool-execution-pipeline --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline .opencode/skills/knowledge-tool-execution-pipeline && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "knowledge-tool-execution-pipeline" agent skill from https://github.com/echoVic/blade-code/tree/main/.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline into .opencode/skills/knowledge-tool-execution-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "knowledge-tool-execution-pipeline", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
knowledge-tool-execution-pipelineCovers ToolExecutor 的验证、worktree 隔离、权限、Hook、审批、并发准入、文件锁、调用重试、LSP/AutoVerify 后处理与结果投影。
Knowledge Tool Execution Pipeline is an agent skill from echoVic/blade-code. Covers ToolExecutor 的验证、worktree 隔离、权限、Hook、审批、并发准入、文件锁、调用重试、LSP/AutoVerify 后处理与结果投影。 Navigate when: 修改工具执行顺序、排查重复副作用、权限或 Hook 覆盖、队列拥塞、取消、同路径写竞争、自动验证或跨表面输出。 Excludes: 工具 schema/注册表定义(见 ../tool-contracts-and-registry/)、具体文件/Shell/Browser 内部语义(见相邻节点)。 Keywords: ToolExecutor, executeToolInvocation, isRetrySafe, PermissionResolver, ToolConcurrencyGate, ConcurrencyScheduler, FileLockManager, AutoVerifyRuntime, StreamingToolExecutor.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Git worktrees. The repository describes itself as: AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers. The licence is MIT.
Read from SKILL.md and the folder at commit 30f8684. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Knowledge Tool Execution Pipeline loads about 2.3k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 425 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from echoVic/blade-code at commit 30f8684, republished under its MIT licence (© echoVic). 425 words, ~2,269 tokens.
.claude/skills/knowledge-tool-execution-pipeline/SKILL.md (or your agent's skills folder).该组件把已注册工具调用变成受控副作用。执行器本身无 Session 持久状态,但通过
ExecutionContext 接收 Session 身份、工作区、权限、取消和交互处理器,并协调多个
进程级与 Session 级资源门。
packages/cli/src/tools/execution/ToolExecutor.ts — 当前平铺执行流程与历史记录packages/cli/src/tools/execution/ToolInvocationRunner.ts — 调用计时与显式安全重试packages/cli/src/tools/execution/PermissionResolver.ts — 规则、模式、Session 批准与敏感路径合并packages/cli/src/tools/execution/ToolExecutionHooks.ts — Pre/Post Hook 适配及参数重建packages/cli/src/tools/execution/ToolConcurrencyGate.ts — 单执行器 shared/exclusive FIFO 屏障packages/cli/src/tools/execution/ConcurrencyScheduler.ts — 全局、Session、ToolKind 多维容量调度packages/cli/src/tools/execution/FileLockManager.ts — canonical 路径锁与稳定顺序多锁packages/cli/src/tools/execution/AutoVerify.ts — 受信任本地编辑后的 Session-owned 类型诊断packages/cli/src/agent/loop/StreamingToolExecutor.ts — 流式预启动、持久化和结果有序交付packages/cli/src/tools/display/ToolResultProjector.ts — durable 结果恢复与表面裁剪ToolExecutor.execute() in packages/cli/src/tools/execution/ToolExecutor.ts — 创建 execution identity 并运行完整流程executeToolInvocation() in packages/cli/src/tools/execution/ToolInvocationRunner.ts — 执行 invocation、记录耗时并实施重试策略StreamingToolExecutor.addTool() in packages/cli/src/agent/loop/StreamingToolExecutor.ts — 决定预启动、排队或拒绝一次流式调用AutoVerifyRuntime.verify() in packages/cli/src/tools/execution/AutoVerify.ts — 对成功文件写入追加相关类型错误ToolExecutorexecute(toolName, params, context) — 合并默认上下文并执行一次完整受控调用executeAll() / executeParallel() — 保序收集批量结果,底层仍通过相同 gate 与 schedulergetExecutionHistory() / getStats() — 读取有界内存执行历史与聚合统计dispose() — 关闭本执行器 gate、取消该 owner 的排队任务并释放注入资源ToolConcurrencyGate.run() — 在一个 executor 内提供 shared 并行和 exclusive FIFO 屏障ConcurrencyScheduler.schedule() — 在进程与 Session 两级按 ToolKind 公平准入FileLockManager.acquireLock() / acquireLocks() — 按 canonical 路径串行写入并避免多锁死锁ToolTurnAdmission.admit() — 将单轮 tool call 数限制为 64PermissionResolver.resolveRulePermission() — 生成权限签名并应用审计代理、模式、Session 批准和敏感文件覆盖runPreToolUseHooks() / runPostToolUseHooks() — 在审批前修改输入、收紧决策并在执行后修改输出executeToolInvocation() — 仅对显式 isRetrySafe invocation 的指定瞬态异常做有界重放formatToolResult() — 补齐 execution ID、工具名和完成时间戳return new ToolExecutor(registry, {
permissionConfig: permissions,
permissionMode,
approvalStore: this.approvalStore,
contextDefaults: { sessionId: this.sessionId, workspaceRoot: this.workspaceRoot },
...(permissionMode === PermissionMode.YOLO ? { autoVerifyRuntime } : {}),
});const result = this.executeTool
? await this.executeTool(toolCall.function.name, params, execContext)
: await this.pipeline.execute(toolCall.function.name, params, execContext);isRetrySafe 缺省时 maxRetries=0,只有显式 opt-in 的 invocation 才会对 EBUSY、EAGAIN、EMFILE、ENFILE 最多重试两次 (packages/cli/src/tools/execution/ToolInvocationRunner.ts, packages/cli/src/tools/core/createTool.ts)execute() 抛出的异常;工具正常返回 { success: false } 不会重试,调用方也不应通过抛错规避领域失败契约 (packages/cli/src/tools/execution/ToolInvocationRunner.ts, packages/cli/src/tools/types/ToolTypes.ts)ToolKind.ReadOnly、isConcurrencySafe、parallelism 与 isRetrySafe 不可互相推导;当前白名单测试只允许 11 个经审计的查询工具重放,Bash、Edit、Write、WriteStdin、Browser 与外部 MCP 均保持不可重放 (packages/cli/tests/unit/tooling/tools/builtin/tool-retry-safety.test.ts, packages/cli/src/tools/types/ToolTypes.ts)packages/cli/src/tools/execution/ToolInvocationRunner.ts, packages/cli/tests/unit/tooling/tools/execution/tool-invocation-runner.test.ts)packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/execution/ToolExecutionHooks.ts)packages/cli/src/tools/execution/PermissionResolver.ts)parallelism: 'shared' 只穿过单执行器批内 gate,仍会受全局/Session/ToolKind scheduler 以及同路径文件锁限制;它不等于无限并发 (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/execution/ConcurrencyScheduler.ts)file_path 或 notebook_path 且仅在 isConcurrencySafe=false 时启用;ApplyPatch 因为是多路径工具,必须在工具内部获取排序后的完整路径锁 (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/builtin/file/applyPatch.ts)formatToolResult() 原地补写 metadata;PostToolUse Hook、LSP 和 AutoVerify 都在它之前运行,因此这些阶段看到的不是最终 execution metadata (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/execution/ToolInvocationRunner.ts)abortedBeforeLaunch=false,不能据此断言副作用未发生;只有 gate/scheduler 前取消才明确是未启动 (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/execution/ToolExecutionResults.ts)ExecutionPipeline.ts 已弃用且只重导出 ToolExecutor;新增阶段类或依赖旧 11 阶段顺序不会进入真实路径 (packages/cli/src/tools/execution/ExecutionPipeline.ts, git:e6a1bef4)packages/cli/src/tools/execution/ToolExecutor.ts)ToolConcurrencyGate 保留同批 exclusive 屏障顺序,ConcurrencyScheduler 再实施进程级和 Session 级总量及 kind 配额,并按 Session 轮转避免饥饿 (packages/cli/src/tools/execution/ToolConcurrencyGate.ts, packages/cli/src/tools/execution/ConcurrencyScheduler.ts)StreamingToolExecutor 只为 allowlist 且 isConcurrencySafe=true 的工具在 Provider 流提交前预启动;parallelism 只决定流结束后的批内屏障,不能扩大预启动集合 (packages/cli/src/agent/loop/StreamingToolExecutor.ts)packages/cli/src/agent/loop/StreamingToolExecutor.ts)RESOURCE_EXHAUSTED/tool_busy 且提示下一轮重试;executor/scheduler 关闭则投影为 dispose/cancel,而不是普通业务失败 (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/execution/ConcurrencyScheduler.ts)runTool 明文维护,减少阶段对象间隐式状态,但修改顺序时必须同步集成测试 (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/tests/integration/tool-executor.test.ts, git:e6a1bef4)packages/cli/src/tools/execution/ConcurrencyScheduler.ts, git:527cb02b)packages/cli/src/agent/runtime/SessionRuntime.ts, packages/cli/src/tools/execution/AutoVerify.ts)ToolResult,而异常路径交给 failExecution 并额外运行 PostToolUseFailure Hook;两条路径的 Hook 行为不同 (packages/cli/src/tools/execution/ToolExecutor.ts, packages/cli/src/tools/execution/ToolExecutionResults.ts)packages/cli/src/tools/execution/ToolApprovalController.ts, packages/cli/src/tools/execution/SessionApprovalStore.ts)type-check script,不调用 npx 猜测工具链 (packages/cli/src/tools/execution/VerifyQueue.ts)packages/cli/src/agent/loop/ToolProgressQueue.ts, packages/cli/src/tools/execution/ConcurrencyScheduler.ts)packages/cli/src/agent/loop/ 是主要调用方:流式路径负责预启动、tool-use 持久化、单轮 64 调用上限和有序回收,最终仍委托 ToolExecutor.execute (packages/cli/src/agent/loop/StreamingToolExecutor.ts, packages/cli/src/agent/loop/executeLoopGenerator.ts)packages/cli/src/agent/runtime/SessionRuntime.ts 为每个 Agent 创建过滤后的 executor,共享 Session approval store,并只在 YOLO 模式注入 AutoVerify (packages/cli/src/agent/runtime/SessionRuntime.ts)packages/cli/src/acp/Session.ts、packages/cli/src/commands/headless.ts、packages/cli/src/server/routes/session.ts 消费统一 ToolResult,再按各自字符预算投影详情,不能绕过 canonical result (packages/cli/src/tools/display/ToolResultProjector.ts)packages/cli/src/hooks/ 通过 Pre/Post/Failure 三类接点影响参数、决策或输出;权限 Hook 的 allow 不能覆盖规则拒绝 (packages/cli/src/tools/execution/ToolExecutionHooks.ts, packages/cli/src/tools/execution/PermissionResolver.ts)packages/cli/src/tools/execution/ToolExecutor.ts)© echoVic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .trae/knowledges/tool-and-automation-platform/tool-execution-pipeline of echoVic/blade-code.
Open the folder on GitHubat commit 30f8684
Knowledge Tool Execution Pipeline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Knowledge Tool Execution Pipeline this skillechoVic/blade-code | 181 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Migrate Core Code to Submodulestinyhumansai/openhuman | 42k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Finishing A Development Branchfarm-fe/farm | 5.6k | 34 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence | |
| Keep Codex Fastvibeforge1111/keep-codex-fast | 1.6k | — | ~3.1k | Automated safety check: Pass | MIT |
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
farm-fe/farm
A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
vibeforge1111/keep-codex-fast
A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.
jamiepine/voicebox
Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.
echoVic/blade-code
Base64 编解码工具,支持编码/解码文本、JSON、二进制文件,自动检测格式,支持批量处理. An agent skill from echoVic/blade-code.
echoVic/blade-code
Review frontend code for best practices, bugs, and improvements.
echoVic/blade-code
Explore and summarize popular GitHub projects. An agent skill from echoVic/blade-code.
echoVic/blade-code
覆盖 Session 级 LSP 配置快照、stdio 进程、文档同步、语义查询、诊断回注、崩溃恢复 和子 Session 继承。进入条件:新增语言服务器、修改 LSP 工具、排查诊断缺失/重复、 处理 worktree 或 ACP 差异、修复进程泄漏或 transport 代际问题。不包含:VS Code 扩展桥接(见…
echoVic/blade-code
覆盖 SkillRegistry、SKILL.md 延迟加载、自定义命令 Markdown 解析、来源覆盖、插件 命名空间、Session 快照和模型/用户调用入口。进入条件:新增 Skill 或命令字段、调整 发现优先级、调试 /command 或 Skill 工具、修改 Prompt 元数据或消费者集成。不包含: 插件安装生命周期(见…
echoVic/blade-code
Covers 领域能力如何包装成内置工具、getBuiltinTools 的 Session 依赖注入、ToolSearch 延迟激活,以及 Goal/Task/Team/Plan/Skill/LSP/MCP/Web/Config/Worktree 适配边界。
Categories
Covers ToolExecutor 的验证、worktree 隔离、权限、Hook、审批、并发准入、文件锁、调用重试、LSP/AutoVerify 后处理与结果投影。. Knowledge Tool Execution Pipeline is an agent skill from echoVic/blade-code./tool-contracts-and-registry/)、具体文件/Shell/Browser 内部语义(见相邻节点)。 Keywords: ToolExecutor, executeToolInvocation, isRetrySafe, PermissionResolver, ToolConcurrencyGate, ConcurrencyScheduler, FileLockManager, AutoVerifyRuntime, StreamingToolExecutor.
Knowledge Tool Execution Pipeline fits situations like: tasks that involve Git worktrees.
Run `npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a claude-code`. Or copy the skill folder (.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline in echoVic/blade-code) into .claude/skills/knowledge-tool-execution-pipeline in your project. Claude Code loads it when a task matches its description.
Run `npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a codex`. Or copy the skill folder (.trae/knowledges/tool-and-automation-platform/tool-execution-pipeline in echoVic/blade-code) into .agents/skills/knowledge-tool-execution-pipeline in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add echoVic/blade-code --skill knowledge-tool-execution-pipeline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-tool-execution-pipeline, .gemini/skills/knowledge-tool-execution-pipeline, .github/skills/knowledge-tool-execution-pipeline and .opencode/skills/knowledge-tool-execution-pipeline in your project.
SKILL.md names no scripts, command-line tools or credentials: Knowledge Tool Execution Pipeline is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Knowledge Tool Execution Pipeline is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Knowledge Tool Execution Pipeline: Finishing a Development Branch (obra/superpowers, 296k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
echoVic (a GitHub user) maintains it in echoVic/blade-code, which has 181 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 27, 2026.
Source: echoVic/blade-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.