@wnlen/agent-execution-template 0.8.16 → 0.8.18

package/README.md

@@ -153,6 +153,31 @@ npx -y @wnlen/agent-execution-template strategy --lang en
 | Upgradeable template | Reuse protocol improvements without losing local project memory. |
 | Doctor checks | Validate required files and template version before running the agent. |
 
+## How Automatic Continuous Execution Works
+
+The user can still give a natural-language goal, for example:
+
+```text
+Build the settings page with profile editing, notification toggles, and export entrypoint
+```
+
+Before execution, the AI decomposes L1 tasks:
+
+```text
+- [ ] L1-1 Profile editing Green
+- [ ] L1-2 Notification toggles Green
+- [ ] L1-3 Export entrypoint Yellow
+```
+
+Because there are two or more L1 tasks, the protocol automatically uses bounded
+continuous execution. Before each L1, the AI plans naturally derived L2/L3 work.
+After completing an L1, it checks and strikes the item, then writes status back
+to `execution_policy.task_tree` in `ai/project/task.md`.
+
+Only Red risk stops for confirmation. Green continues automatically, and Yellow
+continues after local low-risk correction. Every checkpoint must include
+evidence: changed files, commands run, and verification results.
+
 ## Installed Layout
 
 ```text
@@ -162,6 +187,7 @@ ai/
   template/
     VERSION
     bootstrap.md
+    execution-policy.md
     prompt.md
     reconcile.md
     protocol.md
@@ -418,11 +444,25 @@ Run the self-test:
 npm test
 ```
 
+Run the release consistency check:
+
+```bash
+npm run check:release
+```
+
 The test suite verifies the core CLI contract:
 
 - `init` creates the expected protocol and project files.
 - `update` does not overwrite `ai/project/**`.
 - `doctor` reports missing and empty required files correctly.
+- `check:release` verifies versions, template shape, installed protocol state,
+  and the spec's package version.
+
+When maintaining this npm package source checkout, test the local CLI with
+`node bin/agent-execution-template.js <command>`. Use
+`npx -y @wnlen/agent-execution-template <command>` in user projects only.
+Maintainer-local `ai/project/**` bootstrap content should not be committed as
+product changes.
 
 ## Contributing
 

package/README.zh-CN.md

@@ -163,6 +163,29 @@ npx -y @wnlen/agent-execution-template strategy
 | 可升级模板 | 协议可以持续改进，不丢失项目本地记忆。 |
 | Doctor 检查 | 执行前检查必要文件和模板版本。 |
 
+## 自动连续执行怎么工作
+
+用户仍然只需要说自然语言目标，例如：
+
+```text
+实现设置页，包括资料编辑、通知开关和导出入口
+```
+
+AI 会在执行前先拆 L1 任务：
+
+```text
+- [ ] L1-1 资料编辑 Green
+- [ ] L1-2 通知开关 Green
+- [ ] L1-3 导出入口 Yellow
+```
+
+因为 L1 有两个以上，协议会自动使用边界内连续执行。执行每个 L1 前，AI 再规划
+自然衍生的 L2/L3；完成一个 L1 后，在清单中打勾并划掉，同时把状态写回
+`ai/project/task.md` 的 `execution_policy.task_tree`。
+
+只有 Red 风险会停下来让你确认。Green 自动继续，Yellow 只做局部低风险修正后继续。
+每个 Checkpoint 都必须带证据：改了哪些文件、跑了哪些命令、验证结果是什么。
+
 ## 安装后的结构
 
 ```text
@@ -172,6 +195,7 @@ ai/
   template/
     VERSION
     bootstrap.md
+    execution-policy.md
     prompt.md
     reconcile.md
     protocol.md
@@ -425,11 +449,22 @@ License:  MIT
 npm test
 ```
 
+发布前检查：
+
+```bash
+npm run check:release
+```
+
 测试会验证核心 CLI 契约：
 
 - `init` 创建预期的协议和项目文件。
 - `update` 不覆盖 `ai/project/**`。
 - `doctor` 正确报告缺失文件和空的必要文件。
+- `check:release` 验证版本号、模板结构、安装态协议和规格文档一致。
+
+维护这个 npm 包源码仓库时，用 `node bin/agent-execution-template.js <command>`
+测试当前 checkout；用户项目才使用 `npx -y @wnlen/agent-execution-template <command>`。
+维护者本地 `ai/project/**` 初始化内容不应作为产品改动提交。
 
 ## 贡献
 

package/bin/agent-execution-template.js

@@ -13,6 +13,7 @@ const REQUIRED_FILES = [
   "ai/template/LANG",
   "ai/template/VERSION",
   "ai/template/bootstrap.md",
+  "ai/template/execution-policy.md",
   "ai/template/prompt.md",
   "ai/template/reconcile.md",
   "ai/template/protocol.md",
@@ -48,7 +49,13 @@ const TASK_HEALTH_PATTERNS = [
   /^type:\s*/m,
   /^priority:\s*/m,
   /^risk_level:\s*/m,
+  /^readiness:\s*/m,
   /^execution_policy:/m,
+  /^\s+mode:\s*/m,
+  /^\s+activation_rule:\s*/m,
+  /^\s+task_tree:/m,
+  /^\s+risk_gate:/m,
+  /^\s+evidence_required:\s*/m,
   /^model_policy:/m,
   /^refs:/m,
   /^permission:/m
@@ -146,7 +153,12 @@ const TEXT = {
     nextTellAgent: "把这句话发给你的 AI coding 工具:",
     nextRunCommand: "运行这个命令:",
     nextReviewProposal: "已有方向修订提案。先审查提案；确认后对 AI 说:",
+    nextContinuePrompt: "继续推进这个项目。执行前先拆 L1 任务；若 L1 >= 2，自动启用边界内连续执行；只有 Red 风险停下来确认。",
     repairHint: "缺失的 project 推荐文件可通过重新运行 init 安全补齐；已有 ai/project/** 不会被覆盖。",
+    sourceCheckoutNotice: `维护者提示: 当前目录看起来是 @wnlen/agent-execution-template 源码仓库。
+  源码仓库内调试请使用: node bin/agent-execution-template.js <command>
+  用户项目中安装才使用: npx -y @wnlen/agent-execution-template <command>
+  不要把维护者本地初始化产生的 ai/project/** 当成产品改动提交。`,
     permissionDenied: "无法写入目标路径",
     permissionHint: `请检查 ai/** 的归属和权限。常见修复:
   sudo chown -R "$(id -un):$(id -gn)" ai
@@ -250,7 +262,12 @@ Usage:
     nextTellAgent: "Send this to your AI coding tool:",
     nextRunCommand: "Run this command:",
     nextReviewProposal: "A direction amendment proposal exists. Review it first; after confirmation, tell the AI:",
+    nextContinuePrompt: "Continue this project. Before execution, decompose L1 tasks; if L1 >= 2, automatically use bounded continuous execution; only Red risk stops for confirmation.",
     repairHint: "Missing recommended project files can be safely added by running init again; existing ai/project/** files are not overwritten.",
+    sourceCheckoutNotice: `Maintainer note: this directory looks like the @wnlen/agent-execution-template source checkout.
+  In the source repository, test with: node bin/agent-execution-template.js <command>
+  In user projects, install with: npx -y @wnlen/agent-execution-template <command>
+  Do not commit maintainer-local ai/project/** bootstrap content as product changes.`,
     permissionDenied: "Cannot write target path",
     permissionHint: `Check ownership and permissions under ai/**. Common fix:
   sudo chown -R "$(id -un):$(id -gn)" ai
@@ -282,6 +299,17 @@ function readPackageVersion() {
   }
 }
 
+function readTargetPackageName() {
+  const packageFile = path.join(process.cwd(), "package.json");
+  if (!fs.existsSync(packageFile)) return null;
+  try {
+    const pkg = JSON.parse(fs.readFileSync(packageFile, "utf8"));
+    return pkg.name || null;
+  } catch {
+    return null;
+  }
+}
+
 function readInstalledLang() {
   const langFile = path.join(TARGET_AI, "template", "LANG");
   if (!fs.existsSync(langFile)) return DEFAULT_LANG;
@@ -289,6 +317,24 @@ function readInstalledLang() {
   return SUPPORTED_LANGS.has(lang) ? lang : DEFAULT_LANG;
 }
 
+function isSourceCheckout() {
+  return process.cwd() === PACKAGE_ROOT &&
+    readTargetPackageName() === "@wnlen/agent-execution-template";
+}
+
+function commandHint(command) {
+  if (isSourceCheckout()) {
+    return `node bin/agent-execution-template.js ${command}`;
+  }
+  return `npx -y @wnlen/agent-execution-template ${command}`;
+}
+
+function printSourceCheckoutNotice(lang) {
+  if (isSourceCheckout()) {
+    console.log(`${getText(lang).sourceCheckoutNotice}\n`);
+  }
+}
+
 function parseLang(args, fallback = DEFAULT_LANG) {
   let lang = fallback;
   for (let index = 0; index < args.length; index += 1) {
@@ -478,12 +524,14 @@ function init({ lang = DEFAULT_LANG, verbose = false, quiet = false } = {}) {
     .map((change) => ({ ...change, path: path.join("ai/project", change.path) })));
 
   if (!quiet) {
+    const sourceNotice = isSourceCheckout() ? `${text.sourceCheckoutNotice}\n\n` : "";
     console.log(`${text.ready}
 
 ${text.initGuide}
 
+${sourceNotice}
 ${text.files}: ${summarizeChanges(changes, lang)}
-${text.check}: npx -y @wnlen/agent-execution-template doctor
+${text.check}: ${commandHint("doctor")}
 `);
 
     if (verbose) {
@@ -537,12 +585,13 @@ function next({ lang = readInstalledLang() } = {}) {
   }
 
   console.log(`${text.nextTitle}\n`);
+  printSourceCheckoutNotice(lang);
 
   const templatePath = path.join(TARGET_AI, "template");
   const projectPath = path.join(TARGET_AI, "project");
   if (!fs.existsSync(templatePath) || !fs.existsSync(projectPath)) {
     console.log(`${text.nextRunInit}
-  npx -y @wnlen/agent-execution-template init
+  ${commandHint("init")}
 `);
     return;
   }
@@ -583,7 +632,7 @@ function next({ lang = readInstalledLang() } = {}) {
   }
 
   console.log(`${text.nextTellAgent}
-  ${lang === "zh" ? "继续推进这个项目" : "Continue this project"}
+  ${text.nextContinuePrompt}
 `);
 }
 
@@ -669,6 +718,7 @@ function doctor() {
   const lang = readInstalledLang();
   const text = getText(lang);
   console.log(`${text.doctorTitle}\n`);
+  printSourceCheckoutNotice(lang);
   console.log(`${text.templateVersion}: ${readVersion(path.join(TARGET_AI, "template")) || text.unknown}`);
   console.log(`${text.templateLang}: ${lang}\n`);
 
@@ -739,7 +789,7 @@ function doctor() {
   }
 
   if (missing > 0) {
-    console.log(`\n[${text.fail}] ${text.runInit}`);
+    console.log(`\n[${text.fail}] ${commandHint("init")}`);
     process.exitCode = 1;
   } else if (warnings > 0) {
     console.log(`\n[${text.pass}] ${text.readyWithWarnings}`);

package/docs/SPEC.md

@@ -22,7 +22,7 @@ npx 安装协议 -> AI 整理项目上下文 -> 人类确认 -> AI 生成任务
 
 ```text
 Protocol: v0.8
-Package: @wnlen/agent-execution-template@0.8.16
+Package: @wnlen/agent-execution-template@0.8.18
 中文安装: npx -y @wnlen/agent-execution-template init
 英文安装: npx -y @wnlen/agent-execution-template init --lang en
 ```
@@ -181,6 +181,7 @@ ai/
   template/
     VERSION
     bootstrap.md
+    execution-policy.md
     prompt.md
     reconcile.md
     protocol.md
@@ -243,6 +244,7 @@ project 是现场。
 ```text
 ai/template/VERSION
 ai/template/bootstrap.md
+ai/template/execution-policy.md
 ai/template/prompt.md
 ai/template/reconcile.md
 ai/template/protocol.md
@@ -390,12 +392,13 @@ npx -y @wnlen/agent-execution-template doctor
 ```text
 Agent Execution Template 检查
 
-模板版本: 0.8.16
+模板版本: 0.8.18
 模板语言: zh
 
 [通过] ai/template/LANG
 [通过] ai/template/VERSION
 [通过] ai/template/bootstrap.md
+[通过] ai/template/execution-policy.md
 [通过] ai/template/prompt.md
 [通过] ai/template/reconcile.md
 [通过] ai/template/protocol.md
@@ -648,10 +651,11 @@ apply_strategy_update
 
 ## 14. 执行授权策略
 
-执行策略写在：
+执行策略入口写在：
 
 ```text
 ai/project/task.md.execution_policy
+ai/template/execution-policy.md
 ```
 
 默认模式是 `auto`。AI 每次执行前先做任务分解和风险判断，再决定使用
@@ -665,12 +669,13 @@ ai/project/task.md.execution_policy
 - L1 为 2 个或更多时自动使用 `bounded_continuous`；
 - 任一 L1 为 Red 时停止等待人类确认；Green 和 Yellow 不阻塞启动。
 
-`bounded_continuous` 规则：
+`bounded_continuous` 规则集中在 `ai/template/execution-policy.md`。核心要求：
 
 - 按 L1 -> L2 -> L3 执行，执行 L1 前规划 L2，执行 L2 前按需规划 L3；
 - 默认最多 3 层，只有当 L3 仍过大、不可验证或不可回退时才动态增加 L4；
 - 每个任务节点必须有风险评级、预期改动范围、验收方式和证据要求；
 - L1 清单必须用待办列表展示，每完成一个 L1 就打勾并划掉；
+- 执行前和执行中必须把任务树写回 `ai/project/task.md.execution_policy.task_tree`；
 - 默认按 `vertical_slice` 推进，每轮都要产生可检查增量；
 - 每个 Checkpoint 必须包含证据：已改文件、已运行命令、验证结果或无法验证原因；
 - Green 可自动继续；

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wnlen/agent-execution-template",
-  "version": "0.8.16",
+  "version": "0.8.18",
   "description": "Low-friction AI execution protocol template for coding agents.",
   "bin": {
     "agent-execution-template": "bin/agent-execution-template.js"
@@ -14,7 +14,8 @@
   ],
   "scripts": {
     "doctor": "node bin/agent-execution-template.js doctor",
-    "test": "node test/selftest.js"
+    "check:release": "node test/check-release.js",
+    "test": "node test/selftest.js && node test/check-release.js"
   },
   "keywords": [
     "ai",

package/template/en/ai/README.md

@@ -11,6 +11,7 @@ project is the field workspace
 
 - `template/prompt.md`: AI startup prompt.
 - `template/bootstrap.md`: project discovery and context bootstrap prompt.
+- `template/execution-policy.md`: automatic continuous execution, task tree, risk rubric, and checkpoint rules.
 - `template/reconcile.md`: merge new authoritative material into existing project context.
 - `template/VERSION`: installed template version.
 - `template/protocol.md`: bootstrap flow, execution flow, model division, sync rules.
@@ -113,22 +114,5 @@ From a real project back into the template repo:
 - Return only `ai/template/**`.
 - Never return `ai/project/**`.
 
-## Bootstrap Rule
-
-- The human provides intent, hard constraints, and final acceptance.
-- The agent drafts `project/project.md` and relevant `project/refs/*` from existing docs, manifests, refs, and project files.
-- The agent drafts `project/task.md` after the human provides the current task goal.
-- The human reviews and confirms project and task drafts before execution.
-- Bootstrap may write only project context files, plus `project/task.md` when a current task is provided.
-- Bootstrap must not edit source code, tests, configuration, dependency files, generated files, runtime files, result files, or metrics files.
-- Ask at most 3 clarification questions.
-- Ask only when the answer changes scope, risk, permission, or acceptance.
-- Repeated assumptions should become `project/runtime.md` update proposals.
-
-## Model Division Protocol
-
-- Model policy lives in `project/task.md.model_policy`.
-- Use `cheap` by default for routine execution.
-- Use `standard` for moderate implementation complexity.
-- Use `strong` only for planning, risk judgment, architecture review, failure review, or acceptance judgment.
-- Record actual tier, trigger, role, and escalation reason in `project/metrics.json`.
+Detailed execution rules live in `template/protocol.md`,
+`template/bootstrap.md`, `template/execution-policy.md`, and `template/rules/`.

package/template/en/ai/project/task.md

@@ -3,6 +3,7 @@ task_id: ""
 type: "bugfix | feature | refactor | docs | config | test | research | strategy_update | apply_strategy_update"
 priority: "P0 | P1 | P2 | P3"
 risk_level: "low | medium | high"
+readiness: "draft_for_confirmation | ready_to_execute | blocked"
 depends_on_previous_result: false
 execution_policy:
   mode: "auto | normal | bounded_continuous"
@@ -10,7 +11,17 @@ execution_policy:
   max_depth: 3
   allow_depth_4_when_needed: true
   progress_unit: "vertical_slice"
-  task_tree: []
+  task_tree:
+    - id: "L1-1"
+      title: ""
+      risk: "Green | Yellow | Red"
+      status: "pending | running | done | blocked"
+      scope:
+        allowed: []
+        denied: []
+      acceptance: []
+      evidence: []
+      children: []
   checkpoint_budget:
     l1: 0
     l2: 0
@@ -70,8 +81,11 @@ This file is the current execution contract. Prefer generating it in Bootstrap
 Mode from a short human goal plus repository context, then have a human review
 it before execution.
 
-Prefer safe assumptions over extra questions, but do not guess scope, risk,
-permissions, or acceptance.
+Prefer safe assumptions over extra questions. The AI should infer scope, risk,
+permissions, and acceptance from the human goal, project context, and repository
+facts. If inference would cross permission or safety boundaries, or acceptance
+cannot be defined, set `readiness` to `blocked` or mark the relevant task node
+`Red` and wait for human confirmation.
 
 ## Goal
 
@@ -123,6 +137,13 @@ fewer than 2 L1 tasks, use `normal`; if it finds 2 or more L1 tasks, use
 - The AI infers goal, scope, acceptance, permissions, and risk from the human
   goal, project context, and repository facts; the human does not need to
   provide each field upfront.
+- `readiness = ready_to_execute` means no Red preflight item exists and the task
+  may execute.
+- `readiness = draft_for_confirmation` means human confirmation is required
+  before execution.
+- `readiness = blocked` means the task cannot execute and must produce a
+  blocked result.
+- Before execution, write the L1 checklist to `execution_policy.task_tree`.
 - Before execution, list the L1 task checklist; mark each L1 complete with a
   checked and struck-through item.
 - Before executing an L1, plan the naturally derived L2 tasks; if an L2 still
@@ -140,6 +161,8 @@ fewer than 2 L1 tasks, use `normal`; if it finds 2 or more L1 tasks, use
   review is about to start.
 - Every checkpoint must include evidence: changed files, commands run,
   verification results, or why verification was not possible.
+- During execution, update `task_tree` node status: `pending`, `running`,
+  `done`, or `blocked`.
 - After completion, run one final review; only re-check Yellow, Red, failed
   verification, or high-impact modules.
 - Continuous execution does not change model policy; escalate through

package/template/en/ai/template/VERSION

@@ -1 +1 @@
-0.8.16
+0.8.18

package/template/en/ai/template/execution-policy.md

@@ -0,0 +1,109 @@
+# Execution Policy
+
+Do not summarize this file.
+During task execution, use this file to choose `normal` or `bounded_continuous`.
+
+## Default Policy
+
+The default execution policy is `auto`: before each execution, the AI first
+decomposes the task and judges risk, then chooses `normal` or
+`bounded_continuous`. Continuous execution does not depend on a human keyword.
+
+Pre-execution planning must:
+
+- Infer goal, scope, acceptance, permissions, and verification method from the
+  human goal, project context, and repository facts.
+- List the L1 task checklist and assign Green / Yellow / Red risk to each L1.
+- Use `normal` if there are fewer than 2 L1 tasks.
+- Automatically use `bounded_continuous` if there are 2 or more L1 tasks.
+- Stop for human confirmation first if any L1 is Red; Green and Yellow do not
+  block startup.
+- Write the task tree to `execution_policy.task_tree` in `ai/project/task.md`.
+
+## Task Tree
+
+Execute the task tree in L1 -> L2 -> L3 order.
+
+- Before executing an L1, plan its naturally derived L2 tasks.
+- Before executing an L2, plan L3 tasks if it still needs decomposition.
+- Default to at most 3 levels. Add L4 dynamically only when L3 would otherwise
+  be too large, unverifiable, or hard to revert.
+- Every L1/L2/L3/L4 node must have risk, expected edit scope, acceptance method,
+  and evidence requirements.
+- Show the L1 checklist as task items; when an L1 is complete, check it off and
+  strike it through.
+- During execution, update each `task_tree` node status: `pending`, `running`,
+  `done`, or `blocked`.
+
+Recommended node shape:
+
+```yaml
+id: "L1-1"
+title: ""
+risk: "Green | Yellow | Red"
+status: "pending | running | done | blocked"
+scope:
+  allowed: []
+  denied: []
+acceptance: []
+evidence: []
+children: []
+```
+
+## Risk Rubric
+
+Green:
+
+- Inside current task scope;
+- no new permission, command, network access, or destructive action is needed;
+- acceptance is clear;
+- no product direction, core architecture, data structure, security boundary,
+  payment, account, or permission change is needed.
+
+Yellow:
+
+- Still inside current task scope;
+- local uncertainty or local verification failure exists;
+- a low-risk local correction can continue the work;
+- no permission, scope, command, or acceptance expansion is needed.
+
+Red:
+
+- Permission expansion, unallowed command, network access, or destructive action
+  is needed;
+- product direction, core architecture, data structure, security boundary,
+  payment, account, or permission would change;
+- many files must be deleted, a core module must be rewritten, or multiple
+  high-cost options require judgment;
+- acceptance cannot be defined, or task goal materially conflicts with project direction.
+
+Only Red stops for human confirmation. Green continues automatically. Yellow
+continues after local low-risk correction.
+
+## Checkpoint
+
+Emit checkpoints only when risk rises, a boundary is about to change, a vertical
+slice is complete, or final review is about to start. Do not report just to
+spend checkpoint budget.
+
+Every checkpoint must include:
+
+```text
+## Checkpoint
+### Task Tree
+### Progress
+### Completed
+### Evidence
+### Drift Risk: Green / Yellow / Red
+### Recommended Next Step
+### Auto-Continue Decision
+```
+
+Evidence must include changed files, commands run, verification results, or why
+verification was not possible. A purely subjective Green is not valid.
+
+## Model Policy
+
+Continuous execution does not change `model_policy`. Still escalate through
+`model_policy` for planning, architecture, failure review, or acceptance
+disputes, and record the reason in `ai/project/metrics.json`.

package/template/en/ai/template/prompt.md

@@ -9,6 +9,7 @@ First read:
 
 1. `ai/template/protocol.md`
 2. `ai/template/rules/core.md`
+3. `ai/template/execution-policy.md`
 
 Then choose the mode:
 
@@ -64,13 +65,17 @@ In Task Draft Mode:
    risk from the user's current goal, project context, and repository facts; do
    not require the human to provide each field upfront.
 3. Draft `ai/project/task.md` and set `execution_policy.mode` to `auto`.
-4. Before execution, list the L1 checklist and mark each L1 Green / Yellow /
-   Red. Use `normal` if there are fewer than 2 L1 tasks; automatically use
-   `bounded_continuous` if there are 2 or more L1 tasks.
-5. Stop for human confirmation only when a Red preflight item appears. If the
+4. Before execution, list the L1 checklist, mark each L1 Green / Yellow / Red,
+   and write it to `execution_policy.task_tree`. Use `normal` if there are
+   fewer than 2 L1 tasks; automatically use `bounded_continuous` if there are 2
+   or more L1 tasks.
+5. If no Red preflight item exists, set `readiness` to `ready_to_execute`; if
+   human confirmation is needed, set it to `draft_for_confirmation`; if the task
+   cannot execute, set it to `blocked`.
+6. Stop for human confirmation only when a Red preflight item appears. If the
    human asked to execute or continue, and preflight contains only Green /
    Yellow, proceed directly to Execution Mode.
-6. Do not modify source or business files in Task Draft Mode.
+7. Do not modify source or business files in Task Draft Mode.
 
 End Task Draft Mode with:
 
@@ -121,13 +126,15 @@ In Execution Mode, read:
 2. `ai/project/runtime.md`
 3. `ai/project/task.md`
 
-Then perform pre-execution planning: list the L1 checklist, mark each L1 Green
-/ Yellow / Red, and automatically choose `normal` or `bounded_continuous` from
-the L1 count. Plan L2 before executing an L1, and plan L3 as needed before
-executing an L2; default to at most 3 levels, with L4 allowed when needed. When
-an L1 is complete, check it off and strike it through. Only Red stops for human
-confirmation; Green continues automatically, and Yellow continues after local
-low-risk correction. Write results to:
+Then follow `ai/template/execution-policy.md` for pre-execution planning: list
+the L1 checklist, mark each L1 Green / Yellow / Red, and write it to
+`execution_policy.task_tree`. Automatically choose `normal` or
+`bounded_continuous` from the L1 count. Plan L2 before executing an L1, and
+plan L3 as needed before executing an L2; default to at most 3 levels, with L4
+allowed when needed. When an L1 is complete, check it off, strike it through,
+and update the `task_tree` node status. Only Red stops for human confirmation;
+Green continues automatically, and Yellow continues after local low-risk
+correction. Write results to:
 
 - `ai/project/result.json`
 - `ai/project/result.md`