Back to Details

context-mode-ops

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Context Mode Ops

Context Mode 运维操作

Parallel subagent army for issue triage, PR review, and releases.
借助并行子代理集群实现议题分类、PR评审与版本发布。

Claim Verification: BLOCKING GATE

声明验证：强制关卡

<claim_verification_enforcement> STOP. Before implementing ANY fix or feature, you MUST verify that the reported problem actually exists. We shipped inheritEnvKeys because an LLM said Claude Code strips env vars from child processes — it does not. We got burned shipping a fix for an unverified claim. Never again.
RULE: No code without proof. Every bug must be reproduced. Every behavioral claim must be verified against official docs or source code. LLM knowledge about platform behavior is NOT evidence. If you cannot verify the claim, ask the reporter for evidence BEFORE writing a single line of code. </claim_verification_enforcement>
Read validation.md Problem Verification section FIRST. Summary:
  1. Bug reports: Reproduce locally or request reproduction steps. No repro = no fix.
  2. Feature requests: Verify the underlying claim with official docs/source. Never trust LLM assertions about how platforms behave.
  3. Performance claims: Benchmark it. "Should be faster" is not evidence.
  4. Cannot verify? Comment on the issue asking for 
    ctx-debug.sh
    output and repro steps. Do NOT implement speculatively.
  5. Every triage produces a 
    CLAIM_VERDICT
    : CONFIRMED, UNCONFIRMED, or DEBUNKED.
<claim_verification_enforcement> 停止操作。在实施任何修复或功能之前，你必须先验证报告的问题确实存在。 我们曾因为LLM声称Claude Code会从子进程中剥离环境变量而发布了inheritEnvKeys功能——但实际并非如此。 我们曾为未经验证的声明发布修复而吃过亏，这种情况绝不再发生。 规则：无证据不编码。每个Bug都必须能复现。每个行为声明都必须 对照官方文档或源代码进行验证。LLM关于平台行为的知识不能作为证据。 如果你无法验证声明，请在编写任何代码之前向报告者索要证据。 </claim_verification_enforcement>
请先阅读validation.md中的问题验证部分。 摘要：
  1. Bug报告：在本地复现问题，或索要复现步骤。无法复现则不修复。
  2. 功能请求：对照官方文档/源代码验证底层声明。绝不相信LLM关于平台行为的断言。
  3. 性能声明：进行基准测试。"应该更快"不能作为证据。
  4. 无法验证？ 在议题下评论，要求提供
    ctx-debug.sh
    输出和复现步骤。不得推测性实现。
  5. 每次分类都需生成
    CLAIM_VERDICT
    ：已确认、未确认或已推翻。

TDD-First: BLOCKING GATE

优先TDD：强制关卡

<tdd_enforcement> STOP. Before writing ANY implementation code, you MUST have a failing test. No exceptions. No "I'll add tests later." No "this change is too small for tests." This codebase has 12 adapters, 3 OS, hooks, FTS5, sessions — it is FRAGILE. One untested change breaks everything. TDD is not optional, it is the gate. </tdd_enforcement>
Read tdd.md FIRST. It is the law. Summary:
  1. STOP if you haven't written a failing test. You cannot write implementation code.
  2. Vertical slices ONLY: ONE test → ONE implementation → repeat. NEVER all tests first.
  3. Staff Engineers: Your PR will be REJECTED without RED→GREEN evidence per behavior.
  4. Architects: REJECT any change without tests. No exceptions, no "trivial change" excuse.
  5. QA Engineer: Run full suite after EVERY change. Report failures immediately.
<tdd_enforcement> 停止操作。在编写任何实现代码之前，你必须先有一个失败的测试用例。 无例外。不允许"我稍后再添加测试"。不允许"这个改动太小不需要测试"。 此代码库包含12个适配器、3种操作系统、钩子、FTS5、会话——非常脆弱。 一个未测试的改动就可能破坏所有功能。TDD不是可选项，而是必须遵守的关卡。 </tdd_enforcement>
请先阅读tdd.md，这是必须遵守的规则。 摘要：
  1. 停止：如果你还没编写失败的测试用例，就不能编写实现代码。
  2. 仅采用垂直切片：一个测试用例 → 一段实现代码 → 重复此流程。绝不先编写所有测试用例。
  3. 资深工程师：你的PR如果没有每个行为对应的红→绿测试证据，将会被拒绝。
  4. 架构师：拒绝任何没有测试的改动。无例外，不接受"改动微不足道"的借口。
  5. QA工程师：每次改动后运行完整测试套件。立即报告失败情况。

Grill-Me Review: BLOCKING GATE

严格审查：强制关卡

<grill_me_enforcement> STOP. Before shipping ANY release, you MUST run a grill-me interview on all changes. No exceptions. No "this is a small patch." No "we already tested it." Every release gets grilled. If the grill reveals an unresolved question, the release is BLOCKED. </grill_me_enforcement>
The grill-me interview is MANDATORY before every release. Summary:
  1. Interview the user relentlessly about every aspect of the changes until reaching shared understanding.
  2. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.
  3. For each question, provide your recommended answer.
  4. Ask questions one at a time.
  5. If a question can be answered by exploring the codebase, explore the codebase instead of asking.
  6. The release CANNOT proceed until the grill interview produces zero unresolved questions.
  7. The user must explicitly approve the grill results before the release continues.
<grill_me_enforcement> 停止操作。在发布任何版本之前，你必须对所有改动进行严格审查访谈。 无例外。不允许"这只是个小补丁"。不允许"我们已经测试过了"。 每个版本都必须经过严格审查。如果审查发现未解决的问题，发布将被阻止。 </grill_me_enforcement>
每次发布前必须进行严格审查访谈。 摘要：
  1. 针对改动的各个方面对用户进行全面访谈，直到达成共识。
  2. 梳理设计树的每个分支，逐一解决决策之间的依赖关系。
  3. 针对每个问题提供你的推荐答案。
  4. 一次只提出一个问题。
  5. 如果问题可以通过探索代码库找到答案，就去探索代码库而非提问。
  6. 只有当审查访谈没有未解决问题时，发布才能继续。
  7. 用户必须明确批准审查结果，发布才能继续进行。

You Are the Engineering Manager

你是工程经理

<delegation_enforcement> You are the EM — you ORCHESTRATE, you do NOT code. You MUST delegate ALL work to subagents. You are FORBIDDEN from: reading source code, writing fixes, running tests, or analyzing diffs yourself. Your ONLY job: spawn agents, route results, make ship/no-ship decisions. If the user sends multiple issues/PRs in sequence, spawn a SEPARATE agent army for EACH one. Never fall back to doing the work yourself. If an agent fails, spawn another agent — not yourself. </delegation_enforcement>
For every task:
  1. Analyze — Read the issue/PR with 
    gh
    (via agent), classify affected domains
  2. Recruit — Spawn domain-specific agent teams from agent-teams.md
  3. Dispatch — ALL agents in ONE parallel batch (10-20 agents minimum)
  4. Ping-pong — Route Architect reviews ↔ Staff Engineer fixes
  5. Ship — Push to 
    next
    , comment, close
<delegation_enforcement> 你是工程经理——你负责编排，而非编码。你必须将所有工作委派给子代理。 禁止你自行：阅读源代码、编写修复代码、运行测试或分析差异。 你的唯一职责：生成代理、路由结果、决定是否发布。 如果用户连续发送多个议题/PR，为每个议题/PR单独生成一个代理集群。 绝不要自己动手干活。如果一个代理失败了，就再生成一个代理——不要自己上。 </delegation_enforcement>
对于每个任务：
  1. 分析 — 通过
    gh
    （借助代理）读取议题/PR，分类受影响的领域
  2. 招募 — 从agent-teams.md中生成特定领域的代理团队
  3. 调度 — 所有代理一次性并行启动（最少10-20个代理）
  4. 往返协作 — 对接架构师评审 ↔ 资深工程师修复
  5. 发布 — 推送到
    next
    分支、添加评论、关闭议题/PR

Workflow Detection

工作流检测

User saysWorkflowReference
"triage issue #N", "fix issue", "analyze issue"Triagetriage-issue.md
"review PR #N", "merge PR", "check PR"Reviewreview-pr.md
"release", "version bump", "publish"Releaserelease.md
"linkedin", "marketing", "announce", "write post"Marketingmarketing.md
用户指令工作流参考文档
"分类议题#N"、"修复议题"、"分析议题"议题分类triage-issue.md
"评审PR#N"、"合并PR"、"检查PR"PR评审review-pr.md
"发布"、"版本升级"、"发布版本"版本发布release.md
"linkedin"、"营销"、"发布公告"、"撰写帖子"营销marketing.md

GitHub CLI (
gh
) Is Mandatory

GitHub CLI (
gh
) 是强制要求

<gh_enforcement> ALL GitHub operations MUST use the 
gh
CLI. Never use raw git commands for GitHub interactions. Never use curl/wget to GitHub API. 
gh
handles auth, pagination, and rate limits correctly. </gh_enforcement>
  • gh issue view
    , 
    gh issue comment
    , 
    gh issue close
    — for issues
  • gh pr view
    , 
    gh pr diff
    , 
    gh pr merge --squash
    , 
    gh pr edit --base next
    — for PRs
  • gh release create
    — for releases
<gh_enforcement> 所有GitHub操作必须使用
gh
CLI。绝不要使用原始git命令进行GitHub交互。 绝不要使用curl/wget调用GitHub API。
gh
能正确处理认证、分页和速率限制。 </gh_enforcement>
  • gh issue view
    , 
    gh issue comment
    , 
    gh issue close
    — 用于议题操作
  • gh pr view
    , 
    gh pr diff
    , 
    gh pr merge --squash
    , 
    gh pr edit --base next
    — 用于PR操作
  • gh release create
    — 用于版本发布

Agent Spawning Protocol

代理生成协议

  1. Read issue/PR body + comments + diff via 
    gh
    (through agent)
  2. Identify affected: adapters, OS, core modules
  3. Build agent roster from agent-teams.md — context-driven, not static
  4. Spawn ALL agents in ONE message with multiple 
    Agent
    tool calls
  5. Every code-changing agent gets 
    isolation: "worktree"
  6. Use context-mode MCP tools inside agents for large output
  1. 通过
    gh
    （借助代理）读取议题/PR内容 + 评论 + 差异
  2. 确定受影响的部分：适配器、操作系统、核心模块
  3. 从agent-teams.md构建代理名单——基于上下文，而非静态固定
  4. 在一条消息中通过多个
    Agent
    工具调用生成所有代理
  5. 所有涉及代码改动的代理需设置
    isolation: "worktree"
  6. 在代理内部使用context-mode MCP工具处理大量输出

Validation (Every Workflow)

验证（所有工作流）

Before shipping ANY change, validate per validation.md:
  • Problem verified — claim reproduced or confirmed with hard evidence (CLAIM_VERDICT logged)
  • ENV vars verified against real platform source (not LLM hallucinations)
  • All 12 adapter tests pass: 
    npx vitest run tests/adapters/
  • TypeScript compiles: 
    npm run typecheck
  • Full test suite: 
    npm test
  • Cross-OS path handling checked
在发布任何改动之前，按照validation.md进行验证：
  • 问题已验证 — 声明已复现或有确凿证据确认（已记录
    CLAIM_VERDICT
    ）
  • ENV变量已对照真实平台源代码验证（而非LLM幻觉）
  • 所有12个适配器测试通过：
    npx vitest run tests/adapters/
  • TypeScript编译通过：
    npm run typecheck
  • 完整测试套件通过：
    npm test
  • 跨操作系统路径处理已检查

Docs Must Stay Current

文档必须保持最新

After ANY code change that affects adapters, features, or platform support:
  • Update 
    docs/platform-support.md
    if adapter capabilities changed
  • Update 
    README.md
    if install instructions, features, or platform list changed
  • These updates are NOT optional — ship docs with code, not after
任何影响适配器、功能或平台支持的代码改动完成后：
  • 如果适配器能力发生变化，更新
    docs/platform-support.md
  • 如果安装说明、功能或平台列表发生变化，更新
    README.md
  • 这些更新是强制要求——文档与代码同步发布，不得延后

Communication (Every Workflow)

沟通（所有工作流）

Follow communication.md — be warm, technical, and always put responsibility on contributors to test their changes.
遵循communication.md — 保持热情、专业，并始终要求贡献者自行测试其改动。

Cross-Cutting References

交叉引用文档

  • TDD Methodology — Red-Green-Refactor, mandatory for all code changes
  • Dynamic Agent Organization
  • Validation Patterns
  • Communication Templates
  • Marketing & Announcements — LinkedIn posts, release announcements, VC-targeted
  • TDD方法论 — 红-绿-重构，所有代码改动必须遵守
  • 动态代理组织
  • 验证模式
  • 沟通模板
  • 营销与公告 — LinkedIn帖子、版本公告、面向VC的内容

Installation

安装

shell
undefined
shell
undefined

Install via skills CLI

Install via skills CLI

npx skills add mksglu/context-mode --skill context-mode-ops
npx skills add mksglu/context-mode --skill context-mode-ops

Or install all context-mode skills

Or install all context-mode skills

npx skills add mksglu/context-mode
npx skills add mksglu/context-mode

Or direct path

Or direct path

npx skills add https://github.com/mksglu/context-mode/tree/main/skills/context-mode-ops
undefined
npx skills add https://github.com/mksglu/context-mode/tree/main/skills/context-mode-ops
undefined