peaks-loop 4.0.40 → 4.0.42

package/CHANGELOG.md

@@ -1,5 +1,36 @@
 # Changelog
 
+## 4.0.42 — 2026-09-12 (peaks 自己的钩子在每次编辑时报错)
+
+**Highlights**:
+
+1. **`write-gate.js` 每次编辑都向模型报一次"钩子错误" —— 已修。** 这个钩子挂在 `Write|Edit|MultiEdit` 上,判定是 `p.includes('.peaks/_runtime/') ? 0 : 1`。**而开发者真正编辑的每一个文件都不在 `.peaks/_runtime/` 下**,所以它**每次编辑都返回退出码 1**。
+
+   Claude Code 的协议里,**只有 exit 2 会阻断**;任何其他非零退出码都是**非阻断错误** —— 工具照跑,但 transcript 里出现 `<hook> hook error` 加 `Failed with non-blocking status code:` 和 stderr 首行;stderr 为空时显示 `No stderr output`。**这正是用户 Mac 日志里那行。**
+
+   - 更糟的是**文档把它写成了契约**。`HOOKS.md` 与文件头都写着 *"exit 1 = fall through to the gate"* —— **没有 fall-through 这个概念**:所有匹配的 PreToolUse 钩子**并行运行**,结果按 `deny > defer > ask > allow` 合并,不存在"交给下一个"。正确的弃权是 **exit 0 + 无输出**,文档定义为 *"no decision"*。
+   - 所以"静默的 fall-through"实际上是**当时可用的最响的结果**。**行为对所有路径完全不变**(它从不阻断),变的只是它不再一边弃权一边报错。
+   - **同行早就做对了**:`pre-tool-code-gate.sh` 用 exit 0 弃权、只在拒绝路径用 exit 2;`pre-tool-superpowers-bridge.sh` 全路径 exit 0。`write-gate.js` 是唯一的异类 —— 这是收敛一个文件的偏差,不是重新设计。
+   - 三处一起改:代码、`.claude/HOOKS.md` 契约行、以及**钉着 exit-1 映射的 32 用例判定表**(已实测对旧 `decide` 会失败)。判定表现在是"路径清单 + 一条真属性":每条路径都弃权,且两个流都为空。
+
+2. **一个必须说明的保留。** 已知有**独立**报告称钩子 exit 0 时标签仍显示 `hook error`。所以**修完不等于那行必然消失** —— 需要实测;若仍在,用 `claude --debug-file` 查看每个钩子的真实退出码。
+
+**验证**:三个版本常量一致(4.0.42);`tsc -p tsconfig.build.json` exit 0;宽 `tsconfig.json` 保持 **142** 基线;`tests/unit` **188 files / 1794 passed / 3 skipped / 0 failed**。
+
+## 4.0.41 — 2026-09-11 (闸门指导不再鼓励"每次编辑前念一遍")
+
+**Highlights**:
+
+1. **4.0.40 的措辞修好了"误读",但没修"频率" —— 这一版修频率。** 用户在 Mac 上继续工作时反馈:闸门仍然频繁打断。查下去发现**真正被烧掉的时间不是拒绝本身,而是一个仪式** —— 被告诉"预期每个文件被拦一次"之后,模型很自然地选择**预防**:在每次编辑前先把那四条事实念一遍,好让拒绝根本不出现。用户日志里那些重复的 `[Fact-Force Gate] 1..4` 块**是模型自己的话,不是闸门的输出**(闸门自称 `Fact-Forcing`,列的问题也不同)。每次编辑多一次「思考 10 秒 + 复述」,累起来就是他看到的 5 分钟。
+
+   - 现在指导明确要求:**不要预防性复述,闸门问的时候再答。** 拒绝是减速带,不是飞行前检查单。
+
+2. **顺带记录了一条会读成"我退步了"的闸门行为。** 闲置约 30 分钟后,钩子会**删掉自己的状态文件**(`SESSION_TIMEOUT_MS`),清空"已通过"清单 —— 于是**之前已经放行的文件会再次被拦**。不知情的话,这读起来像模型又犯了错。指导里现在写明了:那是闸门在重置,不是你在退步。
+
+3. **同时记下三个可用的旋钮**(闸门自带,非 peaks 引入):`GATEGUARD_EXEMPT_GLOBS`(逗号分隔 glob,加进去的路径直接豁免 —— peaks 写入时**取并集**,不会覆盖你写的)、`GATEGUARD_FACT_FORCE_FULL_DENIALS`(拒绝预算)、`GATEGUARD_DISABLED=1`(整个关掉)。**测试目录这类"没什么事实可建立"的路径,加一条 glob 就不再拦**。
+
+**验证**:三个版本常量一致(4.0.41);`tsc -p tsconfig.build.json` exit 0;宽 `tsconfig.json` 保持 **142** 基线;`tests/unit` **188 files / 1794 passed / 3 skipped / 0 failed**。
+
 ## 4.0.40 — 2026-09-11 (两条被 4.0.39 暴露出来的既有缺陷)
 
 **Highlights**:

package/README-en.md

@@ -140,7 +140,7 @@ Every lane opens with **one slash command**.
 
 | | |
 | --- | --- |
-| **Latest** | [![npm](https://img.shields.io/npm/v/peaks-loop?style=for-the-badge&logo=npm&logoColor=white&color=cb3837)](https://www.npmjs.com/package/peaks-loop) — 4.0.40 (2026-09-11) |
+| **Latest** | [![npm](https://img.shields.io/npm/v/peaks-loop?style=for-the-badge&logo=npm&logoColor=white&color=cb3837)](https://www.npmjs.com/package/peaks-loop) — 4.0.42 (2026-09-12) |
 | **Domains** | Code (`peaks-code`) · Content (`peaks-content`) · Project health (`peaks-doctor`) · Issue sweep (`peaks-issue-fix-orchestrator`) · Custom SOP (`peaks-sop`) · Cross-domain primitives (`peaks-solo` dispatcher · `peaks-resume` · `peaks-status` · `peaks-test` · `peaks-slice-decompose`) |
 | **Sediment pool** | `~/.peaks/` local pool · twice-clean runs auto-promote to a bee · broken runs come back for you to redefine · the bee grows with your taste |
 | **Test suite** | 285+ cases · 4 packages (peaks-loop / peaks-loop-mut / peaks-loop-shared-channel / peaks-loop-shared) · **0 timeouts** · 14 BDD caller-binding edge cases |

package/README.md

@@ -140,7 +140,7 @@ npm i -g peaks-loop
 
 | | |
 | --- | --- |
-| **最新版本** | [![npm](https://img.shields.io/npm/v/peaks-loop?style=for-the-badge&logo=npm&logoColor=white&color=cb3837)](https://www.npmjs.com/package/peaks-loop) — 4.0.40(2026-09-11) |
+| **最新版本** | [![npm](https://img.shields.io/npm/v/peaks-loop?style=for-the-badge&logo=npm&logoColor=white&color=cb3837)](https://www.npmjs.com/package/peaks-loop) — 4.0.42(2026-09-12) |
 | **覆盖域** | 代码(`peaks-code`) · 内容(`peaks-content`) · 项目健康(`peaks-doctor`) · 批量修 issue(`peaks-issue-fix-orchestrator`) · 自定义 SOP(`peaks-sop`) · 通用原语(`peaks-solo` 分诊 / `peaks-resume` 续 / `peaks-status` 看 / `peaks-test` 测 / `peaks-slice-decompose` 切片) |
 | **沉淀池** | `~/.peaks/` 本地池 · 跑两次自动晋升成 bee · 跑翻车让你重定义 · bee 跟着你的口味长 |
 | **测试套件** | 1096 cases · 4 packages (peaks-loop 1015 / runtime 39 / mut 22 / shared-channel 20) · **CI 首次全绿**(ubuntu + windows) · 14 BDD caller-binding coverage |

package/dist/services/hooks/write-gate.js

@@ -31,10 +31,11 @@
  *     `scripts/copy-templates.mjs`), which lets one emitted path string be
  *     valid for both the repo and an installed consumer.
  *
- * Contract (`.claude/HOOKS.md`): exit 0 = allow, exit 1 = fall through to the
- * gate — NOT a deny. Only exit 2 blocks a tool call, and this handler never
- * returns it. This handler's job is to stay silent on the paths the gate is
- * meant to skip.
+ * Contract (`.claude/HOOKS.md`): this handler ALWAYS ABSTAINS: exit 0, no
+ * output, on every path. Only exit 2 blocks a tool call, and this handler
+ * never returns it, so any other non-zero exit is a non-blocking ERROR
+ * rather than a decision. See `decide` below for the correction this file
+ * went through.
  *
  * Path source: the hook payload arrives as JSON on STDIN (Claude Code's
  * documented channel; it appends no argv). `process.argv[2]` is honoured as a
@@ -57,11 +58,31 @@ function candidatePath(payload) {
 }
 
 /**
- * The gate decision: allow (0) only for paths under `.peaks/_runtime/`;
- * everything else falls through to the gate (1).
+ * This handler ABSTAINS on every path, including `.peaks/_runtime/`.
+ *
+ * It used to return 1 for anything outside `.peaks/_runtime/`, documented as
+ * "fall through to the gate". That concept does not exist in the Claude Code
+ * hook protocol. Exit 2 is the only code that blocks; every other non-zero
+ * exit is a NON-BLOCKING ERROR — the action still proceeds, but the transcript
+ * shows `<hook> hook error` followed by `Failed with non-blocking status code:
+ * No stderr output`. The "silent fall-through" was therefore the LOUDEST
+ * available outcome, reported once per edit for every path a developer
+ * actually touches.
+ *
+ * The documented abstention is exit 0 with no output: "no decision". All
+ * matching PreToolUse hooks run in parallel and their results are merged
+ * (`deny` > `defer` > `ask` > `allow`), so abstaining neither approves the call
+ * nor suppresses a sibling's deny — the fact gate still applies to every path
+ * it always applied to.
+ *
+ * Runtime behaviour is unchanged for every path. What changes is that the
+ * handler stops reporting a spurious error while abstaining.
  */
 function decide(p) {
-  return p.includes('.peaks/_runtime/') ? 0 : 1;
+  // The path is still read (it is the payload's whole point) but no longer
+  // branches: every path abstains.
+  void p;
+  return 0;
 }
 
 const ARGV_PATH = typeof process.argv[2] === 'string' ? process.argv[2] : '';
@@ -80,8 +101,10 @@ process.stdin.on('end', () => {
   try {
     payload = JSON.parse(raw);
   } catch {
-    // Malformed or empty payload → no path → deny, which is the same
-    // outcome the old form produced for an absent `process.argv[1]`.
+    // Malformed or empty payload → no path. This is NOT a deny: `decide`
+    // abstains for every input including the empty string, and a deny would
+    // take exit 2. The old comment here said "deny" while returning 1, which
+    // is the non-blocking error — the same misreading this file corrects.
     payload = undefined;
   }
   process.exit(decide(candidatePath(payload) || ARGV_PATH));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "peaks-loop",
-  "version": "4.0.40",
+  "version": "4.0.42",
   "description": "Loop Engineering CLI — workflow primitive / loop guards / evaluators / slice orchestration",
   "author": "SquabbyZ",
   "keywords": [
@@ -101,10 +101,10 @@
     "fzf": "^0.5.2",
     "yaml": "^2.9.0",
     "zod": "^4.4.3",
-    "peaks-loop-internal-runtime": "0.0.25",
-    "peaks-loop-shared": "0.0.74",
-    "peaks-loop-shared-channel": "0.0.42",
-    "peaks-loop-mut": "0.1.38"
+    "peaks-loop-internal-runtime": "0.0.27",
+    "peaks-loop-shared": "0.0.76",
+    "peaks-loop-mut": "0.1.40",
+    "peaks-loop-shared-channel": "0.0.44"
   },
   "devDependencies": {
     "@changesets/cli": "2.31.1",

package/skills/bee/peaks-perf-audit/SKILL.md

@@ -31,13 +31,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # peaks-perf-audit

package/skills/bee/peaks-prd/SKILL.md

@@ -27,13 +27,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/bee/peaks-qa/SKILL.md

@@ -27,13 +27,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/bee/peaks-rd/SKILL.md

@@ -28,13 +28,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/bee/peaks-reviewer/SKILL.md

@@ -23,13 +23,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 ## Single-scope-axis naming convention

package/skills/bee/peaks-sc/SKILL.md

@@ -27,13 +27,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/bee/peaks-security-audit/SKILL.md

@@ -31,13 +31,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # peaks-security-audit

package/skills/bee/peaks-txt/SKILL.md

@@ -27,13 +27,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/bee/peaks-ui/SKILL.md

@@ -27,13 +27,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/peaks-audit/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 ## Single-scope-axis naming convention

package/skills/peaks-code/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 > **Detached sub-agent mode (Phase A, slice 2026-08-10).** When the orchestrator requires true parallelism with isolated context windows and survives orchestrator session exit, dispatch sub-agents with `--mode detached --vendor <claude|codex|copilot>`. The CLI spawns a real OS process via `ProcessSupervisor` (Windows `DETACHED_PROCESS` + `CREATE_NEW_PROCESS_GROUP`, POSIX `setsid` + `nohup`); the child vendor LLM receives a 5–8KB minimum prompt slice (no orchestrator session history) and self-compacts at 0.85 / 0.95 against the vendor window via the `<peaks-auto-compact>` marker (G8 — unlimited spend authorized). Orchestrator MUST emit one line of prose before every detached dispatch: `⏳ Spawning detached sub-agent via <vendor>: rid=<rid> (ETA ~60s)`. Status is read from `.peaks/_runtime/<sid>/detached/<rid>/status.json`; `LifecycleOwner` enforces 100% cleanup of `pid` / `log.txt` / `status.json` / `owner-session` on every exit path. `--no-throttle --max-concurrent <N>` bypasses `ResourceBudgetGuard` (user accepts risk; default max=8). See `references/sub-agent-dispatch.md` §"Detached Mode" for the full contract. Default mode remains `in-process` for backward compat (existing 106+ dispatch tests untouched).

package/skills/peaks-content/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # peaks-content

package/skills/peaks-doctor/SKILL.md

@@ -23,13 +23,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/peaks-final-review/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 ## Single-scope-axis naming convention

package/skills/peaks-ide/SKILL.md

@@ -23,13 +23,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 ---
 

package/skills/peaks-issue-fix-orchestrator/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # peaks-issue-fix-orchestrator

package/skills/peaks-resume/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # Peaks-Loop Code Resume (wrapper)

package/skills/peaks-slice-decompose/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 ## Single-scope-axis naming convention

package/skills/peaks-solo/SKILL.md

@@ -33,13 +33,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # peaks-solo — Dispatcher (分诊员)

package/skills/peaks-sop/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # Peaks-Loop SOP Authoring

package/skills/peaks-status/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # Peaks-Loop Code Status (wrapper)

package/skills/peaks-test/SKILL.md

@@ -22,13 +22,19 @@ mode** — standard *and* 24h. The mode moves the threshold, never the obligatio
 it — the normal way to work here — for every path outside `.peaks/**` (source, tests, docs,
 config); `.peaks/**` writes are exempt.
 
-**Expect one denial per file regardless.** A `PreToolUse` gate (ECC's "Fact-Forcing Gate")
-denies the FIRST edit a session makes to any given path, once, by design. Reading does NOT
-prevent it — the gate keys on the path's first touch, not on whether you read it. **A denial
-is not a failure and the tool is not broken — your edit was NOT applied.** State the facts it
-asks for (importers, affected API, data schemas if any, the user's verbatim instruction) and
-retry the SAME operation; the retry is allowed. Do not switch tools, do not give up, do not
-retry blindly.
+**Expect one denial per file anyway — and do NOT pre-empt it.** A `PreToolUse` gate (ECC's
+"Fact-Forcing Gate") denies the FIRST edit a session makes to any given path, once, by
+design. Reading does NOT prevent it: the gate keys on the path's first touch, not on whether
+you read it. **Do not recite its four questions before every edit** — it asks when it wants
+them, and reciting unprompted burns a round-trip per file for nothing. Answer only when a
+denial actually arrives.
+
+**When one does arrive:** a denial is not a failure and the tool is not broken — your edit
+was NOT applied. State the facts it asks for (importers, affected API, data schemas if any,
+the user's verbatim instruction), then retry the SAME operation. The retry is allowed. Do not
+switch tools, do not give up, do not retry blindly. One more thing worth knowing: an idle gap
+of ~30 minutes clears the gate's "already passed" list, so a file you cleared earlier can be
+denied again after a long pause. That is the gate resetting, not you regressing.
 <!-- /peaks:loop-hygiene -->
 
 # Peaks-Loop Code Test (wrapper)