diff --git a/docs/todo/dynamic-work-graph-design-skill-design.md b/docs/done/dynamic-work-graph-design-skill-design.md
index 17fe841..d763fd6 100644
--- a/docs/todo/dynamic-work-graph-design-skill-design.md
+++ b/docs/done/dynamic-work-graph-design-skill-design.md
@@ -1,7 +1,7 @@
 # 跨 Org Agent 的动态 Work Graph 设计能力——详细设计（SDD）
 
 **日期**: 2026-08-06
-**性质**: 详细设计，对应需求文档 `docs/todo/dynamic-work-graph-design-skill-requirements.md`（条目 E，已确认）。回答该需求文档第 8 节的开放问题。
+**性质**: 详细设计，对应需求文档 `docs/done/dynamic-work-graph-design-skill-requirements.md`（条目 E，已确认）。回答该需求文档第 8 节的开放问题。
 **依赖**：条目 G（`docs/work-graph-parallel-execution-design.md`）已实现——`topological_layers()`/`run_graph()` 已经在生产代码里。
 **状态**: 设计草案，待评审后实施。
 
diff --git a/docs/todo/dynamic-work-graph-design-skill-requirements.md b/docs/done/dynamic-work-graph-design-skill-requirements.md
index a64ce76..a64ce76 100644
--- a/docs/todo/dynamic-work-graph-design-skill-requirements.md
+++ b/docs/done/dynamic-work-graph-design-skill-requirements.md
diff --git a/docs/todo/role-package-abstraction-design.md b/docs/done/role-package-abstraction-design.md
index 44805be..650685b 100644
--- a/docs/todo/role-package-abstraction-design.md
+++ b/docs/done/role-package-abstraction-design.md
@@ -1,7 +1,7 @@
 # 统一 Role Package 抽象层——详细设计（SDD）
 
 **日期**: 2026-08-06
-**性质**: 详细设计，对应需求文档 `docs/todo/role-package-abstraction-requirements.md`（条目 H，需求评审已通过，见 `docs/todo/graph-engineering-open-items.md` H 节的评审记录）。回答该需求文档第 8 节的开放问题。
+**性质**: 详细设计，对应需求文档 `docs/done/role-package-abstraction-requirements.md`（条目 H，需求评审已通过，见 `docs/todo/graph-engineering-open-items.md` H 节的评审记录）。回答该需求文档第 8 节的开放问题。
 **范围确认（用户 2026-08-06）**：FR-3 的 4 张 CHECK 约束表一次性全改，不分阶段。
 **状态**: 设计草案，实施中。
 
diff --git a/docs/todo/role-package-abstraction-requirements.md b/docs/done/role-package-abstraction-requirements.md
index 00ee4f0..0704a5a 100644
--- a/docs/todo/role-package-abstraction-requirements.md
+++ b/docs/done/role-package-abstraction-requirements.md
@@ -16,7 +16,7 @@
 | **context** | `memory: project` → `.claude/agent-memory/{role}/`，git 版本化；但 Work Node 执行时塞进 prompt 的内容是每个调用点临时拼的（`build_prompt(node, outputs)`），没有独立的"context 组装层"抽象 | 局部实现，无统一抽象 |
 | **skills** | `skills/<name>/SKILL.md`，按名字挂进角色的 `skills:` frontmatter | 七项里最成熟、最像"可复用打包单元"的一个 |
 | **applications** | 没有对应的一等概念。架构文档 §7.2 提到 `mcpServers` 字段可以挂专属 MCP server，但 `agent_profile.py::FRONTMATTER` 里三个角色**一个都没配** | 基本空白 |
-| **workflows** | Claude Code 原生 Dynamic Workflows 机制在，但只有 Planner 真正用——`work_graph_plan.py::plan_work_graph()` 的提示词硬编码永远只生成 brd/prd/sdd/benchmark 四个节点，Coder/Validator 走的是更简化的单次 `trigger_org_node()` 调用，没有"先规划图再执行"这条路径（见 `docs/todo/dynamic-work-graph-design-skill-requirements.md`，即条目 E，已确认待做） | 机制存在，不是每个角色都能复用的打包能力 |
+| **workflows** | Claude Code 原生 Dynamic Workflows 机制在，但只有 Planner 真正用——`work_graph_plan.py::plan_work_graph()` 的提示词硬编码永远只生成 brd/prd/sdd/benchmark 四个节点，Coder/Validator 走的是更简化的单次 `trigger_org_node()` 调用，没有"先规划图再执行"这条路径（见 `docs/done/dynamic-work-graph-design-skill-requirements.md`，即条目 E，已确认待做） | 机制存在，不是每个角色都能复用的打包能力 |
 | **permissions** | `tools`/`disallowedTools` per role（如 Validator `disallowedTools: [Edit, Write]`） | 有格式，但有记录在案的真实漏洞：`agent_profile.py` 注释明确写了"scoped Bash patterns（如 `Bash(git commit:*)`）会把 Bash 整个禁掉"，Validator 的 git-mutation 限制实际上退化成了 SOUL.md 里的文字约定，不是工具层强制 |
 | **acceptance criteria** | Benchmark、PASS/FAIL/INCONCLUSIVE、SDD REQ-01~15、`root_cause_trace` 根因归属 | 七项里最成熟的一环 |
 
@@ -32,7 +32,7 @@
 ## 3. 非目标
 
 1. **不要求第一版就实现"运行时自主创建新角色"**。架构文档 §3"关键设计原则 1"明确 Org Graph 结构是人工定义、代码级固定，改动属于架构变更需要人工评审——这条决策不动。本需求要解决的是"人工新增一个角色时，需要改多少处代码/schema"这个摩擦，而不是让系统自己决定要不要新增角色。新增角色依然是人工发起的动作，只是发起方式从"改代码"变成"写一份声明式的 package"。
-2. **不在本文档里解决 workflows 维度的具体落地**——Coder/Validator 缺少动态 Work Graph 规划能力这件事，已经是条目 E（`docs/todo/dynamic-work-graph-design-skill-requirements.md`）的范围，本文档只要求"Role Package 里要有一个字段/引用指向这个角色的 workflow 规划能力"，不重复设计 E 已经在做的事。
+2. **不在本文档里解决 workflows 维度的具体落地**——Coder/Validator 缺少动态 Work Graph 规划能力这件事，已经是条目 E（`docs/done/dynamic-work-graph-design-skill-requirements.md`）的范围，本文档只要求"Role Package 里要有一个字段/引用指向这个角色的 workflow 规划能力"，不重复设计 E 已经在做的事。
 3. **不在本文档里重新解决 permissions 维度的已知漏洞**（scoped Bash disallowedTools 不生效）——这是 Claude Code 平台本身的行为限制，本文档只要求 Role Package 的 permissions 字段要能诚实反映"这条限制实际上是工具层强制还是仅靠文字约定"，不假装这个漏洞已经修复。
 4. **不要求一次性覆盖全部七个维度到同等成熟度**。applications 维度目前是空白，第一版只需要定义清楚"这个维度存在、字段长什么样、允许为空"，不要求马上有真实的 MCP server 集成可用。
 5. **不做通用的"角色市场/角色商店"之类的产品化能力**。这是纯粹的内部抽象层重构，不涉及把角色包装成可分发、可交易的产品单元。
diff --git a/docs/todo/validator-loop-until-dry-skill-design.md b/docs/done/validator-loop-until-dry-skill-design.md
index ce26137..4e93ec0 100644
--- a/docs/todo/validator-loop-until-dry-skill-design.md
+++ b/docs/done/validator-loop-until-dry-skill-design.md
@@ -1,7 +1,7 @@
 # Validator "未知规模扫描收敛" Skill——详细设计（SDD）
 
 **日期**: 2026-08-06
-**性质**: 详细设计，对应需求文档 `docs/todo/validator-loop-until-dry-skill-requirements.md`（条目 B，已确认）。回答该需求文档第 8 节的开放问题。
+**性质**: 详细设计，对应需求文档 `docs/done/validator-loop-until-dry-skill-requirements.md`（条目 B，已确认）。回答该需求文档第 8 节的开放问题。
 **状态**: 设计草案，实施中。
 
 ## 1. 范围确认：纯 Skill，不动执行引擎
diff --git a/docs/todo/validator-loop-until-dry-skill-requirements.md b/docs/done/validator-loop-until-dry-skill-requirements.md
index fa295d1..fa295d1 100644
--- a/docs/todo/validator-loop-until-dry-skill-requirements.md
+++ b/docs/done/validator-loop-until-dry-skill-requirements.md
diff --git a/docs/todo/verifier-fan-out-jury-design.md b/docs/done/verifier-fan-out-jury-design.md
index aac956f..0be4e4e 100644
--- a/docs/todo/verifier-fan-out-jury-design.md
+++ b/docs/done/verifier-fan-out-jury-design.md
@@ -1,7 +1,7 @@
 # 三视角评审团——Work Graph Fan-out 实现——详细设计（SDD）
 
 **日期**: 2026-08-06
-**性质**: 详细设计，对应需求文档 `docs/todo/verifier-fan-out-jury-requirements.md`（条目 F，已确认）。回答该需求文档第 8 节的开放问题。
+**性质**: 详细设计，对应需求文档 `docs/done/verifier-fan-out-jury-requirements.md`（条目 F，已确认）。回答该需求文档第 8 节的开放问题。
 **依赖代码**：`src/root_cause_trace.py`（`judge_root_cause`/`_PERSPECTIVE_FRAMINGS`）、`src/org_level_loop.py`（`run_fix_loop`，唯一真实生产调用方）、`src/work_graph_orchestrate.py`（G 已实现的 `run_graph()`/`topological_layers()`）。
 **状态**: 设计草案，待评审后实施。
 
diff --git a/docs/todo/verifier-fan-out-jury-requirements.md b/docs/done/verifier-fan-out-jury-requirements.md
index 39eba7a..39eba7a 100644
--- a/docs/todo/verifier-fan-out-jury-requirements.md
+++ b/docs/done/verifier-fan-out-jury-requirements.md
diff --git a/docs/todo/work-graph-parallel-execution-design.md b/docs/done/work-graph-parallel-execution-design.md
index ed6fe2e..ed6fe2e 100644
--- a/docs/todo/work-graph-parallel-execution-design.md
+++ b/docs/done/work-graph-parallel-execution-design.md
diff --git a/docs/todo/work-graph-parallel-execution-requirements.md b/docs/done/work-graph-parallel-execution-requirements.md
index 6f70eba..6f70eba 100644
--- a/docs/todo/work-graph-parallel-execution-requirements.md
+++ b/docs/done/work-graph-parallel-execution-requirements.md
diff --git a/docs/todo/work-graph-time-travel-debugging-design.md b/docs/done/work-graph-time-travel-debugging-design.md
index 178d5e8..4b31a09 100644
--- a/docs/todo/work-graph-time-travel-debugging-design.md
+++ b/docs/done/work-graph-time-travel-debugging-design.md
@@ -1,7 +1,7 @@
 # Work Graph 执行历史 Time-Travel 调试——详细设计（SDD）
 
 **日期**: 2026-08-06
-**性质**: 详细设计，对应需求文档 `docs/todo/work-graph-time-travel-debugging-requirements.md`（条目 D，已确认）。回答该需求文档第 8 节的开放问题。
+**性质**: 详细设计，对应需求文档 `docs/done/work-graph-time-travel-debugging-requirements.md`（条目 D，已确认）。回答该需求文档第 8 节的开放问题。
 **状态**: 设计草案，实施中，后端+控制台一起做（用户 2026-08-06 确认）。
 
 ## 1. `ux_work_graph_run_active` 比需求文档描述的风险更小
diff --git a/docs/todo/work-graph-time-travel-debugging-requirements.md b/docs/done/work-graph-time-travel-debugging-requirements.md
index bf7a295..bf7a295 100644
--- a/docs/todo/work-graph-time-travel-debugging-requirements.md
+++ b/docs/done/work-graph-time-travel-debugging-requirements.md
diff --git a/docs/todo/graph-engineering-open-items.md b/docs/todo/graph-engineering-open-items.md
index a3c8276..31daa93 100644
--- a/docs/todo/graph-engineering-open-items.md
+++ b/docs/todo/graph-engineering-open-items.md
@@ -1,7 +1,7 @@
 # Graph Engineering 系列对照笔记——待确认事项清单
 
-**日期**: 2026-08-04（2026-08-05 更新：A/B/D/E/F/G 已确认方向，C 已确认暂不做）
-**性质**: 从三份对照笔记里提取出的全部"待讨论的开放问题"，去重合并后按主题整理，供逐条确认方案。每条确认后会展开成独立的需求文档（参考 `docs/work-graph-parallel-execution-requirements.md` 的产出方式），本文件本身只做索引和现状追踪，不写详细方案。
+**日期**: 2026-08-04（2026-08-06 更新：A/B/D/E/F/G/H 全部已实现，C 已确认不做——全部条目均已resolve，本文件继续作为这条主线的活索引保留在 `docs/todo/`，不迁入 `docs/done/`，因为它会随新一批对照笔记/差距检查持续追加条目，见 H 的加入方式）
+**性质**: 从三份对照笔记里提取出的全部"待讨论的开放问题"，去重合并后按主题整理，供逐条确认方案。每条确认后会展开成独立的需求文档（参考 `docs/done/work-graph-parallel-execution-requirements.md` 的产出方式，条目落地后连同设计文档一并移入 `docs/done/`），本文件本身只做索引和现状追踪，不写详细方案。
 **来源文档**：
 - `docs/reference/graph-engineering-1000-agents-5-steps.diff-with-graphlemon.md`（简称"5 步版对照"）
 - `docs/reference/graph-engineering-vs-loop-engineering-overview.diff-with-graphlemon.md`（简称"综述版对照"）
@@ -36,7 +36,7 @@
 
 ## B. loop-until-dry 要不要在 Validator 落地
 
-**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/validator-loop-until-dry-skill-requirements.md` + 设计文档 `docs/todo/validator-loop-until-dry-skill-design.md`
+**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/validator-loop-until-dry-skill-requirements.md` + 设计文档 `docs/done/validator-loop-until-dry-skill-design.md`
 
 **来源**：5 步版对照 §4 开放问题 1
 
@@ -62,7 +62,7 @@
 
 ## D. Time-travel 调试要不要立项
 
-**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/work-graph-time-travel-debugging-requirements.md` + 设计文档 `docs/todo/work-graph-time-travel-debugging-design.md`
+**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/work-graph-time-travel-debugging-requirements.md` + 设计文档 `docs/done/work-graph-time-travel-debugging-design.md`
 
 **来源**：综述版对照 §6
 
@@ -78,7 +78,7 @@
 
 ## E. Planning Skill 提示词强化——识别可并行节点 + 通用 Work Graph 设计能力
 
-**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/dynamic-work-graph-design-skill-requirements.md` + 设计文档 `docs/todo/dynamic-work-graph-design-skill-design.md`
+**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/dynamic-work-graph-design-skill-requirements.md` + 设计文档 `docs/done/dynamic-work-graph-design-skill-design.md`
 
 **来源**：综述版对照 §7 开放问题 3 + 14 步版对照 §3 开放问题 2（同一主题：让 Planning 阶段更早识别并行机会）
 
@@ -92,7 +92,7 @@
 
 ## F. 三视角评审团机制要不要推广到其他验证点
 
-**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/verifier-fan-out-jury-requirements.md` + 设计文档 `docs/todo/verifier-fan-out-jury-design.md`
+**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/verifier-fan-out-jury-requirements.md` + 设计文档 `docs/done/verifier-fan-out-jury-design.md`
 
 **来源**：综述版对照 §7 开放问题 4 + 14 步版对照 §3 开放问题 4（同一主题）
 
@@ -106,7 +106,7 @@
 
 ## G. Work Graph 节点并行执行（Python 线程池方案）
 
-**状态**：✅ 已实现（2026-08-06）→ 需求文档见 `docs/work-graph-parallel-execution-requirements.md`
+**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/work-graph-parallel-execution-requirements.md` + 设计文档 `docs/done/work-graph-parallel-execution-design.md`
 
 **来源**：14 步版对照 §3 开放问题 1
 
@@ -120,7 +120,7 @@
 
 ## H. 统一 Role Package 抽象层
 
-**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/role-package-abstraction-requirements.md` + 设计文档 `docs/todo/role-package-abstraction-design.md`
+**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/role-package-abstraction-requirements.md` + 设计文档 `docs/done/role-package-abstraction-design.md`
 
 **来源**：不属于三份 Graph Engineering 对照笔记，是用户对照 Agentic Enterprise 产品目标（"role + context + skills + applications + workflows + permissions + acceptance criteria；all essentially are context for intelligent computing"）单独提出的差距检查，2026-08-06。
 
diff --git a/skills/design-dynamic-work-graph/SKILL.md b/skills/design-dynamic-work-graph/SKILL.md
index 5b7a589..8296a74 100644
--- a/skills/design-dynamic-work-graph/SKILL.md
+++ b/skills/design-dynamic-work-graph/SKILL.md
@@ -11,7 +11,7 @@ tags:
   - orchestration
 metadata:
   origin: graphlemon-native
-  related: [G（并行执行）docs/work-graph-parallel-execution-design.md, E docs/todo/dynamic-work-graph-design-skill-design.md]
+  related: [G（并行执行）docs/work-graph-parallel-execution-design.md, E docs/done/dynamic-work-graph-design-skill-design.md]
 platforms: [linux, macos, windows]
 ---
 
diff --git a/skills/unknown-scope-defect-sweep/SKILL.md b/skills/unknown-scope-defect-sweep/SKILL.md
index a321ec2..0c98aaa 100644
--- a/skills/unknown-scope-defect-sweep/SKILL.md
+++ b/skills/unknown-scope-defect-sweep/SKILL.md
@@ -11,7 +11,7 @@ tags:
   - sweep
 metadata:
   origin: graphlemon-native
-  related: [qa-task-validation, docs/todo/validator-loop-until-dry-skill-design.md]
+  related: [qa-task-validation, docs/done/validator-loop-until-dry-skill-design.md]
 platforms: [linux, macos, windows]
 ---
 
diff --git a/src/agent_profile.py b/src/agent_profile.py
index a696eaf..07bba91 100644
--- a/src/agent_profile.py
+++ b/src/agent_profile.py
@@ -33,7 +33,7 @@ read by this module's own Python code; `json.load` is the zero-risk choice,
 no hand-rolled parser. role.json content is deliberately a REFERENCE
 manifest, not a content copy: `identity.soul_md_path`/`agents_md_path` still
 point at the same `agents/<org_node>/SOUL.md`/`AGENTS.md` files, unmoved --
-see docs/todo/role-package-abstraction-design.md §2 for why keeping the
+see docs/done/role-package-abstraction-design.md §2 for why keeping the
 existing identity files as the single source of prose content makes the
 migration's "deployed output must stay byte-identical" requirement close to
 automatic (only the frontmatter's data SOURCE changed, not the body-assembly
diff --git a/src/org_level_loop.py b/src/org_level_loop.py
index 740b479..6def114 100644
--- a/src/org_level_loop.py
+++ b/src/org_level_loop.py
@@ -17,7 +17,7 @@ def run_fix_loop(conn, task_id, target_folder_path, bug_description, context, fi
     function doesn't add its own fallback for that, matching 04-P's own
     "升级人工" answer to disagreement).
 
-    **F (2026-08-06, docs/todo/verifier-fan-out-jury-design.md)**: root
+    **F (2026-08-06, docs/done/verifier-fan-out-jury-design.md)**: root
     cause judgment now runs as a real Work Graph fan-out (each perspective
     is its own Work Node with its own clean context) instead of three
     sequential Python closures calling org_node_trigger.trigger_org_node --
diff --git a/src/root_cause_trace.py b/src/root_cause_trace.py
index 72f616d..7e5be79 100644
--- a/src/root_cause_trace.py
+++ b/src/root_cause_trace.py
@@ -15,7 +15,7 @@ concrete question each perspective asks is a prompt-engineering concern for
 the caller (see real_validator_perspective below for the real-call version),
 not this module's.
 
-**F (2026-08-06, docs/todo/verifier-fan-out-jury-design.md)**: judge_root_cause
+**F (2026-08-06, docs/done/verifier-fan-out-jury-design.md)**: judge_root_cause
 above is the closure-based implementation -- each perspective is a Python
 function call, sequentially, in the SAME process/context. Kept as-is (not
 replaced): it's the cheap path for scenarios that don't need worktree/Work
diff --git a/src/schema.py b/src/schema.py
index 1cc0ed1..4270e0c 100644
--- a/src/schema.py
+++ b/src/schema.py
@@ -84,7 +84,7 @@ CREATE TABLE skill (
     -- ('planner','coder','validator')) -- relaxed to a plain non-empty-string
     -- check so a new role, added purely via roles/<role_id>/role.json (no
     -- schema.py/agent_profile.py code change), isn't rejected by a stale
-    -- hardcoded enum. See docs/todo/role-package-abstraction-design.md §4.
+    -- hardcoded enum. See docs/done/role-package-abstraction-design.md §4.
     owner_org_node TEXT NOT NULL CHECK (owner_org_node != ''),
     file_path TEXT NOT NULL,
     current_git_commit_sha TEXT NOT NULL,
diff --git a/src/test_org_level_loop.py b/src/test_org_level_loop.py
index 2eb4833..2d54200 100644
--- a/src/test_org_level_loop.py
+++ b/src/test_org_level_loop.py
@@ -5,7 +5,7 @@ Testing constraint). Real coverage is in src/test_org_level_loop_e2e.py
 
 **F (2026-08-06)**: root-cause judgment now runs through
 root_cause_trace.judge_root_cause_via_work_graph (a real Work Graph fan-out,
-see docs/todo/verifier-fan-out-jury-design.md), so the 3 perspective calls
+see docs/done/verifier-fan-out-jury-design.md), so the 3 perspective calls
 are mocked at work_graph_execute.write_workflow_script/execute_work_graph
 (same boundary as test_work_graph_orchestrate.py), not at
 org_node_trigger.trigger_org_node -- that mock is now only used for the
diff --git a/src/test_work_graph_fork.py b/src/test_work_graph_fork.py
index 5eb95ef..f5f4613 100644
--- a/src/test_work_graph_fork.py
+++ b/src/test_work_graph_fork.py
@@ -1,7 +1,7 @@
 """D (2026-08-06) tests: work_graph_fork.py, mocked at the claude
 subprocess boundary (CLAUDE.md Testing constraint) -- same pattern as
 test_work_graph_orchestrate.py. Covers the requirements doc's acceptance
-standards 1-3 (docs/todo/work-graph-time-travel-debugging-requirements.md).
+standards 1-3 (docs/done/work-graph-time-travel-debugging-requirements.md).
 
 Run: python3 -m unittest src.test_work_graph_fork -v
 """
diff --git a/src/work_graph_fork.py b/src/work_graph_fork.py
index 9393665..14a1f1f 100644
--- a/src/work_graph_fork.py
+++ b/src/work_graph_fork.py
@@ -3,7 +3,7 @@ work_graph_run from an already-'done' work_node_execution, substituting a
 human-provided output for that node and re-executing everything strictly
 downstream of it for real, while every other node reuses the original
 run's persisted output_payload untouched. See
-docs/todo/work-graph-time-travel-debugging-design.md for the full design.
+docs/done/work-graph-time-travel-debugging-design.md for the full design.
 
 **Output substitution, not re-prompting** (design doc §2, resolving the
 requirements doc's FR-1 ambiguity): the fork point's own output_payload is
diff --git a/src/work_graph_orchestrate.py b/src/work_graph_orchestrate.py
index a870b3f..21fab05 100644
--- a/src/work_graph_orchestrate.py
+++ b/src/work_graph_orchestrate.py
@@ -352,7 +352,7 @@ def run_graph(
     independent work, no reason to throw away completed work), then raised
     together as `WorkGraphLayerError` once the whole layer has settled.
     One real limitation, accepted deliberately (see
-    `docs/todo/work-graph-parallel-execution-design.md` §6): a node
+    `docs/done/work-graph-parallel-execution-design.md` §6): a node
     waiting on a quota-backoff sleep inside `run_work_node` blocks the
     thread pool worker running it, which in turn blocks the layer barrier
     even after every sibling has finished -- Python threads have no clean
diff --git a/src/work_graph_plan.py b/src/work_graph_plan.py
index 8a26d16..e4fa23e 100644
--- a/src/work_graph_plan.py
+++ b/src/work_graph_plan.py
@@ -80,7 +80,7 @@ _PROMPT_TEMPLATE = (
 # E (2026-08-06): the generic, cross-Org-Agent path -- used for every
 # org_node OTHER than 'planner'. Planner's own doc-writing chain stays on
 # _PROMPT_TEMPLATE above unchanged (zero regression risk, see
-# docs/todo/dynamic-work-graph-design-skill-design.md §3): that chain is a
+# docs/done/dynamic-work-graph-design-skill-design.md §3): that chain is a
 # fixed architectural constant (brd->prd->sdd->benchmark->...), not
 # something that should vary call to call, whereas Coder/Validator's
 # sub-tasks have no such fixed small vocabulary of node types. Each node