litclaude-ai 0.3.45 → 0.3.46

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.3.46 - 2026-08-16 — ready-to-paste native `/goal` guidance
+
+- Add structured `READY_TO_PASTE` guidance for unavailable native goal binding,
+  including one bounded `/goal` condition that the user can submit manually in
+  the current Claude Code session.
+- Keep automatic slash-command submission unavailable and redact shell-like
+  objective fragments before they reach hook context.
+
 ## 0.3.45 - 2026-08-15 — documentation surface refresh
 
 - Simplify the English and Korean README guides and pin their packaged cover

package/README.md

@@ -1,4 +1,4 @@
-<p align="center"><img src="https://cdn.jsdelivr.net/npm/litclaude-ai@0.3.45/cover.png" width="100%" alt="LitClaude — Claude Code-native workflow package" /></p>
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/litclaude-ai@0.3.46/cover.png" width="100%" alt="LitClaude — Claude Code-native workflow package" /></p>
 
 <h1 align="center">LitClaude</h1>
 <p align="center">
@@ -9,7 +9,7 @@
 </p>
 <p align="center">
   <img src="https://img.shields.io/badge/npm-litclaude--ai-cb3837" alt="npm: litclaude-ai" />
-  <img src="https://img.shields.io/badge/version-0.3.45-2ea44f" alt="version 0.3.45" />
+  <img src="https://img.shields.io/badge/version-0.3.46-2ea44f" alt="version 0.3.46" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" alt="Claude Code plugin" />
   <img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT license" />
 </p>
@@ -50,13 +50,13 @@ npx --yes litclaude-ai@latest install
 For a reproducible install, pin the current package version:
 
 ```bash
-npm view litclaude-ai@0.3.45 version
+npm view litclaude-ai@0.3.46 version
 ```
 
-If that lookup returns `0.3.45`, the exact install is available:
+If that lookup returns `0.3.46`, the exact install is available:
 
 ```bash
-npx --yes litclaude-ai@0.3.45 install
+npx --yes litclaude-ai@0.3.46 install
 ```
 
 Otherwise, wait for explicit human publication before using that pin. Check the
@@ -138,6 +138,9 @@ reports degraded mode and keeps the local `litgoal` ledger authoritative. Set
 The route attempts native goal binding honestly: it inspects available goal tools,
 never replaces a different active goal, and falls back to the local ledger when the
 host does not expose model-facing goal controls.
+When that fallback is needed, the hook emits `READY_TO_PASTE` with one bounded
+`/goal` line for the user to copy, paste, and send in the current session; it
+never enters or submits the command itself.
 
 `/start-work` owns the schema-3 bounded-authority start-work lifecycle. An approved
 plan can resume only through this exact route:

package/README_ko-KR.md

@@ -1,4 +1,4 @@
-<p align="center"><img src="https://cdn.jsdelivr.net/npm/litclaude-ai@0.3.45/cover.png" width="100%" alt="LitClaude — Claude Code-native workflow package" /></p>
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/litclaude-ai@0.3.46/cover.png" width="100%" alt="LitClaude — Claude Code-native workflow package" /></p>
 
 <h1 align="center">LitClaude</h1>
 <p align="center">
@@ -9,7 +9,7 @@
 </p>
 <p align="center">
   <img src="https://img.shields.io/badge/npm-litclaude--ai-cb3837" alt="npm: litclaude-ai" />
-  <img src="https://img.shields.io/badge/version-0.3.45-2ea44f" alt="version 0.3.45" />
+  <img src="https://img.shields.io/badge/version-0.3.46-2ea44f" alt="version 0.3.46" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" alt="Claude Code plugin" />
   <img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT license" />
 </p>
@@ -52,13 +52,13 @@ npx --yes litclaude-ai@latest install
 뒤 고정합니다.
 
 ```bash
-npm view litclaude-ai@0.3.45 version
+npm view litclaude-ai@0.3.46 version
 ```
 
-조회 결과가 `0.3.45`이면 exact install을 사용할 수 있습니다.
+조회 결과가 `0.3.46`이면 exact install을 사용할 수 있습니다.
 
 ```bash
-npx --yes litclaude-ai@0.3.45 install
+npx --yes litclaude-ai@0.3.46 install
 ```
 
 그렇지 않으면 명시적인 human publication을 기다립니다. Pin은 그 뒤에 사용합니다.
@@ -140,6 +140,9 @@ host가 model-facing worktree lane을 제공하면 `EnterWorktree`를 사용합
 이 route는 native goal binding을 정직하게 시도합니다. 사용 가능한 goal tool을
 확인하고 다른 active goal을 교체하지 않으며, host가 model-facing goal control을
 제공하지 않으면 local ledger로 전환합니다.
+이 fallback이 필요하면 hook이 `READY_TO_PASTE`와 함께 복사·붙여넣기·전송할
+`/goal` 한 줄을 제공합니다. LitClaude가 현재 세션에 직접 입력하거나 전송하지는
+않습니다.
 
 `/start-work`는 schema-3 bounded-authority start-work lifecycle을 관리합니다.
 승인된 plan의 resume은 다음 exact route만 사용합니다.

package/RELEASE_CHECKLIST.md

@@ -1,6 +1,6 @@
 # LitClaude Release Checklist
 
-Status: `litclaude-ai@0.3.45` is the current release candidate — exact canonical
+Status: `litclaude-ai@0.3.46` is the current release candidate — exact canonical
 frontend corpus plus Claude-native `autoresearch`, `autoconference`, and `wikify`
 workflow-family integration. It byte-pins the frontend library, legal companions,
 family source closures, and adapters through independent commitments and package
@@ -45,9 +45,9 @@ side-effect-free, the launcher starts only a separate Claude Code
 print/background worker, and the release preserves the Korean polishing
 command, strict multi-agent review pipeline, fidelity guardrails, package
 hygiene checks, native route gates, and safe start-work handoff behavior.
-`package.json` is aligned to `0.3.45`,
-`plugins/litclaude/.claude-plugin/plugin.json` is aligned to `0.3.45`, and the
-plugin-local MCP server reports `0.3.45`.
+`package.json` is aligned to `0.3.46`,
+`plugins/litclaude/.claude-plugin/plugin.json` is aligned to `0.3.46`, and the
+plugin-local MCP server reports `0.3.46`.
 
 This release carries the v0.2.2 Dynamic workflow hardening surfaces:
 `/dynamic-workflow`, `workflow-check --json`, native `/goal` fallback guidance,
@@ -280,9 +280,9 @@ checkout and from an isolated install of the packed tarball:
 Before requesting publication approval, confirm these artifacts from the current
 checkout:
 
-- `package.json` version is `0.3.45`.
-- `plugins/litclaude/.claude-plugin/plugin.json` version is `0.3.45`.
-- `plugins/litclaude/bin/litclaude-mcp.js` reports server version `0.3.45`.
+- `package.json` version is `0.3.46`.
+- `plugins/litclaude/.claude-plugin/plugin.json` version is `0.3.46`.
+- `plugins/litclaude/bin/litclaude-mcp.js` reports server version `0.3.46`.
 - Prompt-hook tests cover bundled `SKILL.md` body injection for bare `hyperplan`, `litresearch`, `lit research`, `init-deep`, and explicit leading `$start-work`; diagnostic/copy mentions stay inert while leading natural-language `lit start work` stays BLOCKED.
 - `lit search` and `lit query` route to `/litclaude:litresearch` without activating on slash mentions, code spans, or non-lit prompts.
 - Litresearch web lanes require public API/feed preference, validator-first checks, route traces, prompt-injection quarantine, and honest auth/paywall/private-data stop reasons.

package/docs/hooks.md

@@ -54,6 +54,7 @@ verdicts: [PASS, FAIL, BLOCKED]
 - Claude Code hook JSON containing `continue: true`, `hookSpecificOutput.hookEventName`, and route-specific `additionalContext`.
 - Optional `systemMessage` only for active LitClaude route guidance.
 - `BLOCKED:` text for natural-language start-work, unavailable native goal binding, disabled Dynamic workflow, or gated agent-team setup.
+- Unavailable native goal binding also includes `READY_TO_PASTE` and one bounded `/goal` command for the user to copy, paste, and send; the hook never enters or submits it.
 
 ## #contract.evidence
 
@@ -281,8 +282,9 @@ Source-backed capability note: the observed `UserPromptSubmit` hook surface can
 add `additionalContext` or block; it cannot replace the prompt or run another
 slash command. If goal tools are unavailable or not exposed in the running
 Claude Code session, the hook returns explicit `BLOCKED:` / degraded-mode
-guidance, does not claim native goal success, keeps the local `litgoal` evidence
-ledger authoritative, and may suggest `/goal <completion condition>` or
+guidance plus a `READY_TO_PASTE` command, does not claim native goal success,
+keeps the local `litgoal` evidence ledger authoritative, and may suggest
+`/goal <completion condition>` or
 `claude -p "/goal <completion condition>"` for the native user surface.
 For a separate worker session, `litclaude-ai litgoal native-worker --condition
 "<completion condition>"` builds a dry-run native `/goal` worker command; adding

package/docs/native-goal-surface.md

@@ -36,6 +36,17 @@ Adapt filenames only when the local ledger reports a different authoritative
 path. The condition does not make the ledger self-validating; recorded evidence
 still needs the normal LitClaude review gates.
 
+## Hook runtime contract
+
+When the current session does not expose model-facing goal tools, the native
+binding helper returns `status: "blocked-unavailable"` with
+`nextAction: "ready-to-paste"`, a bounded `condition`, and the exact `command`.
+UserPromptSubmit includes a `READY_TO_PASTE` instruction containing that command.
+The model should show the unchanged line and ask the user to copy, paste, and
+send it as a new message in the current session. This is a user-confirmed
+submission, not automatic invocation: LitClaude cannot enter the command,
+replace the current prompt, or turn it into a tool call.
+
 This documentation does not add a fake command, MCP method, or hook dispatch.
 The native-goal binding itself does not auto-install a goal, mutate a transcript,
 inject keystrokes, or claim success based on prompt context alone. Package

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "litclaude-ai",
-  "version": "0.3.45",
+  "version": "0.3.46",
   "description": "Claude Code-native workflow distribution.",
   "type": "module",
   "bin": {

package/plugins/litclaude/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "litclaude",
   "description": "Claude Code-native workflow plugin with a bounded-authority start-work lifecycle.",
-  "version": "0.3.45",
+  "version": "0.3.46",
   "author": {
     "name": "LitClaude contributors"
   },

package/plugins/litclaude/bin/litclaude-hook.js

@@ -682,7 +682,11 @@ const isDiagnosticLiteralPrompt = (prompt) =>
 const objectiveTail = (prompt) => {
   const raw = withoutCode(prompt);
   const match = /\blit(?:work)?\b\s*(.*)$/isu.exec(raw);
-  return normalizeGoalObjective(match?.[1] ?? raw);
+  const tail = (match?.[1] ?? raw).replace(
+    /^\s*(?:-loop|-plan|goal|plan|workflow|dynamic\s+workflow|work)\b\s*/iu,
+    "",
+  );
+  return normalizeGoalObjective(tail);
 };
 
 const goalBindingContext = ({ discipline, prompt, activeGoal }) => {

package/plugins/litclaude/bin/litclaude-mcp.js

@@ -9,7 +9,7 @@ import {
 } from "../lib/wikify-knowledge.mjs";
 
 const protocolVersion = "2024-11-05";
-const serverVersion = "0.3.45";
+const serverVersion = "0.3.46";
 
 const publicSourceReadTool = {
   name: "public_source_read",

package/plugins/litclaude/commands/litgoal.md

@@ -95,6 +95,11 @@ and avoid clobbering a different active goal without explicit replacement. When
 goal tools are unavailable, return explicit `BLOCKED:` / degraded-mode wording
 instead of claiming native success, and record clear criteria and evidence in
 the local ledger.
+If the hook reports `READY_TO_PASTE`, reproduce its exact `/goal <condition>`
+line for the user, instruct them to copy, paste, and send it in the current
+Claude Code session, and wait for a new user message. LitClaude cannot enter or
+send that command on the user's behalf; do not silently rewrite it or convert it
+into a tool call.
 For broad goal execution, use Dynamic workflow when Claude Code exposes it, and
 use `claude --worktree <short-name> --tmux` only when isolated worktree
 execution is needed.

package/plugins/litclaude/lib/native-goal-binding.mjs

@@ -5,6 +5,13 @@ const secretPatterns = [
   /(?:api[_-]?key|token|secret|password)\s*=\s*\S+/giu,
 ];
 
+const unsafeCommandPatterns = [
+  /\b(?:rm|rmdir)\s+-r(?:f)?\b[^;&|\n]*/giu,
+  /\b(?:sudo|eval|exec)\b[^;&|\n]*/giu,
+  /\b(?:npm|pnpm|yarn)\s+(?:publish|unpublish)\b[^;&|\n]*/giu,
+  /\bgit\s+(?:push|reset|clean)\b[^;&|\n]*/giu,
+];
+
 const normalizeSpaces = (value) => value.replace(/\s+/gu, " ").trim();
 
 export const normalizeGoalObjective = (value) => {
@@ -17,7 +24,11 @@ export const normalizeGoalObjective = (value) => {
     (text, pattern) => text.replace(pattern, "[REDACTED]"),
     cleaned,
   );
-  return normalizeSpaces(redacted).slice(0, MAX_OBJECTIVE_CHARS).trim();
+  const safe = unsafeCommandPatterns.reduce(
+    (text, pattern) => text.replace(pattern, "[UNSAFE_COMMAND_REDACTED]"),
+    redacted,
+  );
+  return normalizeSpaces(safe).slice(0, MAX_OBJECTIVE_CHARS).trim();
 };
 
 const canonical = (value) => normalizeGoalObjective(value).toLowerCase();
@@ -27,6 +38,27 @@ const activeGoalObjective = (activeGoal) => {
   return normalizeGoalObjective(activeGoal.objective ?? activeGoal.goal ?? activeGoal.text ?? "");
 };
 
+const readyToPasteCondition = (objective) =>
+  `Continue until this LitClaude objective is complete: ${objective}. Stop only after required evidence is recorded and no unresolved blocker remains.`;
+
+const readyToPasteGuidance = (objective) => {
+  const condition = readyToPasteCondition(objective);
+  const command = `/goal ${condition}`;
+  return {
+    nextAction: "ready-to-paste",
+    condition,
+    command,
+    message: [
+      "Native goal binding attempt: BLOCKED: native `/goal` not programmatically bound.",
+      "READY_TO_PASTE: LitClaude cannot enter or send a command to the current Claude Code session.",
+      "Copy, paste, and send this line in the current Claude Code session:",
+      command,
+      "After sending it, keep the durable `litgoal` ledger authoritative for criteria, evidence, checkpoints, and blockers.",
+      "Separate non-interactive fallback: run `claude -p \"/goal <completion condition>\"` in a new session.",
+    ].join("\n"),
+  };
+};
+
 export const buildNativeGoalBindingGuidance = ({ objective, activeGoal } = {}) => {
   const normalizedObjective = normalizeGoalObjective(objective);
   const activeObjective = activeGoalObjective(activeGoal);
@@ -46,8 +78,10 @@ export const buildNativeGoalBindingGuidance = ({ objective, activeGoal } = {}) =
     };
   }
 
+  const ready = readyToPasteGuidance(normalizedObjective);
   return {
     status: "blocked-unavailable",
-    message: "Native goal binding attempt: BLOCKED: native `/goal` not programmatically bound. Evidence: the supported UserPromptSubmit hook surface can add context or block, but does not expose a run-slash-command channel; this session exposes no callable get_goal/create_goal/update_goal tools to LitClaude. I will not claim host goal activation. To bind Claude Code's native user surface, paste `/goal <completion condition>` in the session, or run `claude -p \"/goal <completion condition>\"` in a non-interactive flow. Until then, keep the durable `litgoal` ledger authoritative for objective, criteria, evidence, checkpoints, and blockers.",
+    ...ready,
+    message: `${ready.message}\nEvidence: the supported UserPromptSubmit hook surface can add context or block, but does not expose a run-slash-command channel; this session exposes no callable get_goal/create_goal/update_goal tools to LitClaude.`,
   };
 };

package/plugins/litclaude/skills/litgoal/SKILL.md

@@ -136,6 +136,14 @@ record in the local litgoal ledger. Never auto-type `/goal`, never claim
 slash-command activation without evidence, and never mark a goal complete until
 the local litgoal criteria have passed.
 
+When the UserPromptSubmit context contains `READY_TO_PASTE`, preserve the exact
+`command` line it provides. Show it as the one command the user should copy,
+paste, and send in the current Claude Code session, explain that LitClaude
+cannot enter or send it on the user's behalf, and wait for the user's next
+message before treating native goal submission as user-confirmed. Do not
+silently rewrite the condition, turn it into a tool call, or offer a different
+active goal for replacement without explicit approval.
+
 When the user explicitly wants a separate native `/goal` worker rather than the
 current TUI session, use the package CLI launcher. It is dry-run by default: