@litfamily/litclaude 1.0.22 → 1.0.24

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## 1.0.24 - 2026-10-12
+
+- The LIT card no longer drops to idle while background work is still running. When the main turn ends after starting background subagents or a workflow, the card stays at work and counts the running agents until the last one finishes, and it never reads `DONE` while an agent is still busy. A workflow's agents now count too, and a subagent that finishes in the middle of a turn no longer dims the chips of the request that is still running. An agent that never reports back stops counting after 30 quiet minutes, so it cannot hold the card at work.
+- The README shows the LIT card as it really appears: resting before anything runs, at work with the skill's chip lit, and after the turn, when the chip dims into the recent list.
+- The README walks through automatic handoff with terminal pictures: turning it on with `lit-handoff auto on 65`, checking and turning it off, the reminder to run `/compact`, and the two shell variables that switch it on before Claude Code starts.
+- The install section has a prompt you can paste into a coding agent so it installs LitClaude for you. The agent shows what would change and waits for your yes, runs the doctor, and reminds you to restart Claude Code.
+- The office runtime now pins sharp 0.35.5, and the README Studio cover templates use sharp 0.35.5 and source-map-js 1.2.2.
+
+## 1.0.23 - 2026-10-12
+
+- The LIT card above the prompt now stays on screen for the whole session, so you can still see the status after the work ends. It is a small four-row card in the colours of your status line. The top edge names the workflow and the current phase. Below it are the plan, work and review steps with the progress of the plan or goal. Every LitClaude skill that runs gets its own chip, several at once. A chip is bright while its request is running and dims into a recent list when the turn ends. At the bottom are the context use, the five-hour usage window and the Git branch. The card fits narrow terminals by leaving out the least important parts and never wraps. The `band` setting now defaults to `always`; `auto` brings back the old behaviour, and `off` hides the card.
+- The status line no longer shows the `🔥 LIT IGNITED · <workflow> 🔥` mark. It took up so much room that the model, context and usage figures were cut off, and the card now shows which workflow is active.
+- Project rules now fit in the skill context when LitClaude is installed under a long folder path. Before, a long install path could cut off the first line of a rule or leave the rules out entirely.
+
 ## 1.0.22 - 2026-10-11
 
 - The README is shorter for first-time readers. It says what LitClaude does, how to install it and what to type first, and the detailed material now lives in docs pages (guide, skills, Jev, development) in English and Korean. The GitHub page also plays a short film of a real session.

package/README.md

@@ -1,14 +1,14 @@
-<p align="center"><picture><source media="(prefers-reduced-motion: reduce)" srcset="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/cover-motion-still.webp" /><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/cover-motion.webp" width="100%" alt="LitFamily motion cover: five armored robots power on one by one, the LitClaude robot wakes with glowing eyes and a lit frame, then LITFAMILY and KEEP THE WORK LIT. light up." /></picture></p>
+<p align="center"><picture><source media="(prefers-reduced-motion: reduce)" srcset="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/cover-motion-still.webp" /><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/cover-motion.webp" width="100%" alt="LitFamily motion cover: five armored robots power on one by one, the LitClaude robot wakes with glowing eyes and a lit frame, then LITFAMILY and KEEP THE WORK LIT. light up." /></picture></p>
 
 <h1 align="center">LitClaude</h1>
 <p align="center"><strong>Keep the work lit.</strong></p>
 <p align="center">A Claude Code plugin that helps every session plan the work, build it, check it, and leave a note the next session can pick up.</p>
 <p align="center">
-  <img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/readme/badge-version.svg" alt="1.0.22" />
-  <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/LICENSE"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/readme/badge-license.svg" alt="MIT license" /></a>
+  <img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/readme/badge-version.svg" alt="1.0.24" />
+  <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/LICENSE"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/readme/badge-license.svg" alt="MIT license" /></a>
 </p>
 <p align="center">
-  <a href="https://github.com/wjgoarxiv/litclaude#readme">Full guide and skills gallery on GitHub</a> · <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/README_ko-KR.md">한국어</a>
+  <a href="https://github.com/wjgoarxiv/litclaude#readme">Full guide and skills gallery on GitHub</a> · <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/README_ko-KR.md">한국어</a>
 </p>
 
 Add `lit` to a Claude Code prompt and Claude pins the goal, writes a failing test first,
@@ -73,7 +73,7 @@ the `/plugin` menu.
 ## More
 
 - [Full guide and skills gallery on GitHub](https://github.com/wjgoarxiv/litclaude#readme)
-- [Privacy and network behavior](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/privacy.md)
-- [Migration and ownership conflicts](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/migration.md)
-- [Release history](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/CHANGELOG.md)
-- [MIT license](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/LICENSE)
+- [Privacy and network behavior](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/privacy.md)
+- [Migration and ownership conflicts](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/migration.md)
+- [Release history](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/CHANGELOG.md)
+- [MIT license](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/LICENSE)

package/README_ko-KR.md

@@ -1,14 +1,14 @@
-<p align="center"><picture><source media="(prefers-reduced-motion: reduce)" srcset="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/cover-motion-still.webp" /><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/cover-motion.webp" width="100%" alt="LitFamily 모션 커버: 다섯 로봇 패널이 차례로 켜지고, LitClaude 로봇의 눈과 테두리가 빛난 뒤 LITFAMILY와 KEEP THE WORK LIT. 문구가 밝아지는 영상" /></picture></p>
+<p align="center"><picture><source media="(prefers-reduced-motion: reduce)" srcset="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/cover-motion-still.webp" /><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/cover-motion.webp" width="100%" alt="LitFamily 모션 커버: 다섯 로봇 패널이 차례로 켜지고, LitClaude 로봇의 눈과 테두리가 빛난 뒤 LITFAMILY와 KEEP THE WORK LIT. 문구가 밝아지는 영상" /></picture></p>
 
 <h1 align="center">LitClaude</h1>
 <p align="center"><strong>Keep the work lit.</strong></p>
 <p align="center">Claude Code에서 세션마다 계획하고, 만들고, 확인한 뒤 다음 세션이 이어받을 기록을 남기게 돕는 플러그인입니다.</p>
 <p align="center">
-  <img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/readme/badge-version.svg" alt="1.0.22" />
-  <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/LICENSE"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/assets/readme/badge-license.svg" alt="MIT license" /></a>
+  <img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/readme/badge-version.svg" alt="1.0.24" />
+  <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/LICENSE"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/assets/readme/badge-license.svg" alt="MIT license" /></a>
 </p>
 <p align="center">
-  <a href="https://github.com/wjgoarxiv/litclaude/blob/main/README_ko-KR.md">전체 안내와 스킬 갤러리는 GitHub에서</a> · <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/README.md">English</a>
+  <a href="https://github.com/wjgoarxiv/litclaude/blob/main/README_ko-KR.md">전체 안내와 스킬 갤러리는 GitHub에서</a> · <a href="https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/README.md">English</a>
 </p>
 
 Claude Code 프롬프트에 `lit`을 붙이면 Claude가 목표를 고정하고, 실패하는 테스트를 먼저 쓰고,
@@ -71,7 +71,7 @@ LitClaude는 프로젝트 상태를 `.litclaude/`에 두고, 그 안의 `.gitign
 ## 더 보기
 
 - [전체 안내와 스킬 갤러리 (GitHub)](https://github.com/wjgoarxiv/litclaude/blob/main/README_ko-KR.md)
-- [개인정보와 네트워크 동작](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/privacy.md)
-- [이전과 소유권 충돌](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/docs/migration.md)
-- [변경 이력](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/CHANGELOG.md)
-- [MIT 라이선스](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.22/LICENSE)
+- [개인정보와 네트워크 동작](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/privacy.md)
+- [이전과 소유권 충돌](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/docs/migration.md)
+- [변경 이력](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/CHANGELOG.md)
+- [MIT 라이선스](https://cdn.jsdelivr.net/npm/@litfamily/litclaude@1.0.24/LICENSE)

package/docs/assets/readme/badge-version.svg

@@ -1 +1 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="146" height="20" role="img" aria-label="release: 1.0.22"><title>release: 1.0.22</title><g shape-rendering="crispEdges"><rect width="49" height="20" fill="#080d14"/><rect x="49" width="97" height="20" fill="#ff6337"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="110"><text x="255" y="140" textLength="390" transform="scale(.1)">release</text><text x="965" y="140" textLength="870" transform="scale(.1)" fill="#080D14">1.0.22</text></g></svg>
+<svg xmlns="http://www.w3.org/2000/svg" width="146" height="20" role="img" aria-label="release: 1.0.24"><title>release: 1.0.24</title><g shape-rendering="crispEdges"><rect width="49" height="20" fill="#080d14"/><rect x="49" width="97" height="20" fill="#ff6337"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="110"><text x="255" y="140" textLength="390" transform="scale(.1)">release</text><text x="965" y="140" textLength="870" transform="scale(.1)" fill="#080D14">1.0.24</text></g></svg>

package/docs/hooks.md

@@ -346,36 +346,73 @@ itself. LitClaude's is `plugins/litclaude/hooks/lit-mod.mjs`, named under `modul
 `hooks/hooks.json` next to the settings hooks above. It installs with the plugin and needs no
 setup. The status line stays as it is; the band adds a live layer above the prompt.
 
-While LitClaude work is active in the session (a start-work plan, an open litgoal goal, a lit
-discipline on a running turn, or live subagents) a band sits above the prompt:
-
-- A ribbon of rounded pills, `LIT · PLAN · WORK n/m · REVIEW`, then a pink-to-cyan progress bar
-  whose leading cell fades in as it fills, the next task, the number of lanes, and the autoloop
-  count with the time left in its 30-minute budget. It is fitted to the terminal width, with Hangul
-  and emoji counted as two cells; parts drop in a fixed order when the row is narrow.
-- A card with a round border when two or more lanes run or a warning needs a row: the phase
-  line, the next task, each lane with its state and elapsed time, and the gates (plan saved,
-  interface probe, motion gate, auto-handoff).
-- Amber when something needs attention: a lane quiet for more than 10 minutes, or context within
-  five points of the auto-handoff percent (the WORK pill crossfades to amber and the ribbon shows
-  `ctx 76% → 80%`). A failed interface probe adds a red row and turns the border red.
-- A notice row and a toast when a gate fires: lit-plan not saved, interface probe pending or
-  failed, motion gate, context near the auto-handoff percent, auto-handoff fired.
-- A completion moment when the last task is checked, the work completes or the goal is met: a
-  light passes over the brand, embers scatter, and `COMPLETE` shows for about a second.
+From the first prompt to the end of the session a LIT card sits above the prompt. It keeps the
+same four rows whether LitClaude is working or idle, and takes the status line's accent
+(`LITCLAUDE_HUD_ACCENT`, read from the installed status line command), so the card and the
+status line read as one family:
+
+```
+╭─ [🔥 LIT] · lit-loop ─────────────────────────── WORK ● ─╮
+│ ● PLAN ━━ [WORK] ━━ ○ REVIEW              goal ██░░░ 2/5 │
+│ skills [⚡ lit-plan] [⚡ litresearch] [↯ lit-docx]        │
+╰─ ctx 42% ▰▰▱▱▱ · 5h 31% · git main ──────────────────────╯
+```
+
+The brackets stand for the ends of filled pills: rounded caps from the icon font with `nerd`
+glyphs, one cell of the pill's colour with `basic`. The brand is a pink pill, the active phase
+and the skills of this request are pills on the accent with dark text, and skills from earlier
+requests are muted grey pills.
+
+- The top edge names the discipline the prompt hook ignited (the last one, dimmed, while the
+  session is idle; `ready` before any) and, on the right, the current phase: `WORK ●`, `idle`,
+  or `DONE ✓` during the finish. While a subagent is still running the card stays at work
+  (`LIVE ●` when no phase is active) and never reads `DONE`, even after the main turn ended.
+- The phase row lights `PLAN ━━ WORK ━━ REVIEW` from the start-work plan, the litgoal goal and
+  the discipline (the active phase as a pill, done phases `●`, the rest `○`), and on its right shows a pink-to-cyan progress bar with the checked tasks or
+  passed criteria (`goal ✓ 5/5` once a goal is met), the number of live subagents (`● 2 lanes`), the autoloop
+  count with the time left in its 30-minute budget, and `ctx 76% → 80%` when the context is
+  within five points of the auto-handoff percent.
+- The chips row shows each LitFamily skill that fired as a pill: a Skill tool call naming a LitClaude
+  skill, a typed `/litclaude:<name>`, or bare `lit` routing seen through the ignition record.
+  A skill fired in the current request is bright, with a short light passing over its name as
+  it arrives; when the turn completes it dims into the `recent` list, and a new firing brightens
+  it again. Chips follow a dim `skills` label; those that do not fit collapse into a muted `+N`. Skills of other plugins never get a chip.
+  With no chip yet, the row shows the next task while work runs, or how to start (`lit <task>`)
+  while idle.
+- The bottom edge carries the live figures from the status line: context fill, the five-hour
+  rate window and the Git branch (read from `HEAD`, across a linked worktree).
+- A notice takes the chips row for a few seconds, with a toast, when a gate fires: lit-plan not
+  saved, interface probe pending or failed, motion gate, context near the auto-handoff percent,
+  auto-handoff fired. The completion moment takes it when the last task is checked, the work
+  completes or the goal is met: a light passes over the brand, embers scatter, and `COMPLETE`
+  shows for about a second.
+- Amber or red when something needs attention: a lane quiet for more than 10 minutes turns the
+  border amber and puts `⚠ <lane> quiet for 12m` on the bottom edge; a failed interface probe
+  turns it red.
+
+Subagents and teammates come from Claude Code's agent list. A workflow script's agents never
+appear there, so the mod also records every agent at `agent.spawn` and counts it until that
+agent's own `turn.complete` arrives. A subagent's turn ending does not end the main turn: the
+chips of the current request stay bright until the main turn completes. An agent the list shows
+as ended stops counting at once, and one quiet for 30 minutes (no tool call, no status change)
+stops counting too, so a crashed or lost agent cannot hold the card at work.
+
+The card is the terminal's width up to 80 columns and every row is fitted to it, with Hangul and
+emoji counted as two cells. Nothing wraps: on a narrow terminal the Git branch goes first, then
+the rate window, the lanes, the autoloop count and the long phase labels (`P ━ W ━ R`).
 
 The spinner gains ` · <discipline> · n/m` after its ellipsis. `/lit-evidence` opens a pane with
 three tabs (keys `1`, `2`, `3`): the goal's criteria with their last evidence, blockers and the
-newest litgoal ledger entries; the lanes; and the gates. When the session is idle the band is not
-drawn at all.
+newest litgoal ledger entries; the lanes; and the gates.
 
 Motion: entrances pop in 60 ms apart with a slight overshoot (160 ms each), fills and colour
 changes ease in and out (300 ms and 140 ms), notices slide in over 220 ms and leave over 150 ms,
-and the finish lasts at most 1.2 s. The band's `Client` element animates on Claude Code's frame
+a chip's arrival light runs 400 ms (a plain fade under `subtle`, nothing under `off`), and the
+finish lasts at most 1.2 s. The band's `Client` element animates on Claude Code's frame
 clock only while something moves and stops its timer as soon as everything settles. In Claude
 Code 2.1.292 a terminal row whose only change is a non-ASCII glyph is not repainted, so every
 moving part changes ASCII text or colour: bar cells are coloured spaces, embers are ASCII sparks,
-and a glyph swaps only together with its words.
+a chip's light moves over its ASCII name, and a glyph swaps only together with its words.
 
 Options, in `/config` under LitClaude (stored in `pluginConfigs`):
 
@@ -383,14 +420,15 @@ Options, in `/config` under LitClaude (stored in `pluginConfigs`):
 | --- | --- | --- |
 | `motion` | `full`, `subtle` (no overshoot, shimmer or embers, shorter), `off` (final frames only) | `full` |
 | `glyphs` | `auto` (Nerd glyphs when the icon font is installed), `nerd`, or `basic` | `auto` |
-| `band` | `auto` (only while work is active), `always`, `off` | `auto` |
+| `band` | `always` (the whole session, idle included), `auto` (only while work is active or a skill of this request is lit), `off` | `always` |
 
 Unknown values fall back to the default. The fields are plain strings with no `options` list on
 purpose: Claude Code 2.1.270 and older refuse to load a plugin whose `userConfig` has one, and
 that would take every LitClaude hook down with it. Nerd glyphs reach only the terminal; the
 desktop app and the other surfaces always get the basic set.
 
-The rounded pill caps (U+E0B6, U+E0B4) and icons come from a Nerd Font. `litclaude-ai install
+The icons on `nerd` (the rounded pill caps U+E0B6 and U+E0B4, the chip bolt and the branch mark)
+come from a Nerd Font. `litclaude-ai install
 --icon-font`, or a Yes to the install question (default No), adds the symbols-only Nerd Font,
 Symbols Nerd Font Mono (MIT), to the per-user font folder (`~/Library/Fonts` on macOS,
 `~/.local/share/fonts` on Linux, then `fc-cache -f` if present; on Windows it prints how to
@@ -403,8 +441,9 @@ records the two files, `uninstall` removes only those (and only while unchanged)
 prints `ICON_FONT:`. With `glyphs` on `auto`, the band checks those font folders by stat at session
 start and says what it decided on the `/lit-evidence` gates tab.
 
-The mod is read-only. It reads LitClaude's own state and nothing else: the ignition record in
-the per-user temp folder, `.litclaude/boulder.json` (found the way the hooks find it, across a
+The mod is read-only. It reads LitClaude's own state, the Git `HEAD` of the working directory and
+the merged settings (for the status line's accent) and nothing else: the ignition record in the
+per-user temp folder, `.litclaude/boulder.json` (found the way the hooks find it, across a
 linked worktree), and under the outermost Git root's `.litclaude/` the litgoal goal, autoloop
 counter and ledger, the lit-plan, interface-probe and motion turn records, and the auto-handoff
 settings and session record. Each file must be a regular file under its size cap that resolves

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@litfamily/litclaude",
-  "version": "1.0.22",
+  "version": "1.0.24",
   "description": "Claude Code plugin: add lit to a prompt and Claude plans, tests, checks and reviews the work, then leaves a handoff for the next session.",
   "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": "1.0.22",
+  "version": "1.0.24",
   "author": {
     "name": "LitClaude contributors"
   },
@@ -30,8 +30,8 @@
     "band": {
       "type": "string",
       "title": "LIT band",
-      "description": "When the band shows above the prompt: auto (only while LitClaude work is active), always or off.",
-      "default": "auto"
+      "description": "When the LIT card shows above the prompt: always (the whole session, idle included), auto (only while LitClaude work is active or a skill of this request is lit) or off.",
+      "default": "always"
     }
   }
 }

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

@@ -14,7 +14,7 @@ import {
   toneText,
 } from "../lib/hud-accent-palette.mjs";
 import { latestUsageTokensCached } from "../lib/cache-measurement.mjs";
-import { ignitionStatePath, readIgnitionState, renderIgnitionSegment } from "../lib/hud-ignition.mjs";
+import { ignitionStatePath } from "../lib/hud-ignition.mjs";
 import { jevHudState } from "../lib/jev-skill-hint.mjs";
 import { resolveProjectStateRoot } from "../lib/project-state-root.mjs";
 import { recordContextUsage, resolveAutoHandoff } from "../lib/auto-handoff.mjs";
@@ -344,13 +344,10 @@ const main = async () => {
   const contextText = contextPct === null
     ? `${text("ctx")} ${text(`?/${windowText}`)}`
     : `${text("ctx")} ${accent("[")}${makeContextBar(contextPct)}${accent("]")} ${text(`${contextPct}%/${windowText}`)}`;
-  const ignition = renderIgnitionSegment(readIgnitionState(status.session_id), {
-    depth: plainOutput ? "plain" : colorDepth,
-  });
   const effort = effortLabel(status);
   const jev = jevBadge(status);
   const autoHandoff = autoHandoffSegment(status, knownContextPct);
-  const line = `${prefix}${ignition ? ` ${ignition}` : ""} ${accent("|")} ${text(model)}${effort ? ` ${text(effort)}` : ""}${jev ? ` ${jev}` : ""} ${accent(sep)} ${contextText}${autoHandoff ? ` ${accent(sep)} ${autoHandoff}` : ""}${usageText}${git ? ` ${accent(sep)} ${text("git")} ${text(git)}` : ""}`;
+  const line = `${prefix} ${accent("|")} ${text(model)}${effort ? ` ${text(effort)}` : ""}${jev ? ` ${jev}` : ""} ${accent(sep)} ${contextText}${autoHandoff ? ` ${accent(sep)} ${autoHandoff}` : ""}${usageText}${git ? ` ${accent(sep)} ${text("git")} ${text(git)}` : ""}`;
   process.stdout.write(`${line}\n`);
 
   const lastMessage = latestUserMessage(status.transcript_path);

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

@@ -9,7 +9,7 @@ import {
 } from "../lib/wikify-knowledge.mjs";
 
 const protocolVersion = "2024-11-05";
-const serverVersion = "1.0.22";
+const serverVersion = "1.0.24";
 
 const publicSourceReadTool = {
   name: "public_source_read",

package/plugins/litclaude/hooks/lit-band-client.mjs

@@ -39,6 +39,6 @@ export default function LitBand(props, surface) {
   if (surface.state?.live !== holder) surface.setState({ live: holder, now: holder.now });
 
   if (!model.visible && !timelineBusy(holder.timeline, holder.now, profile)) return empty();
-  const frame = composeBand(model, sampleTimeline(holder.timeline, holder.now, profile), { columns: props.columns, glyphs: props.glyphs });
+  const frame = composeBand(model, sampleTimeline(holder.timeline, holder.now, profile), { columns: props.columns, glyphs: props.glyphs, accent: props.accent });
   return renderBand(surface.elements, frame);
 }

package/plugins/litclaude/hooks/lit-mod.mjs

@@ -1,7 +1,9 @@
-// LitClaude's Claude Code mod (hooks/hooks.json `modules`). It draws the LIT band above the prompt
-// while LitClaude work is active, adds the discipline and progress to the spinner, raises gate
-// notices, and serves /lit-evidence. It is read-only: it reads LitClaude's own state files through
-// lib/mod/state.mjs and the host's live figures, and never writes, spawns, fetches or calls a model.
+// LitClaude's Claude Code mod (hooks/hooks.json `modules`). It draws the LIT card above the prompt
+// for the whole session (the `band` setting can limit it to active work or turn it off), lights a
+// chip for each LitFamily skill that fires, adds the discipline and progress to the spinner, raises
+// gate notices, and serves /lit-evidence. It is read-only: it reads LitClaude's own state files and
+// the Git HEAD through lib/mod/state.mjs, the settings for the status line's accent, and the host's
+// live figures, and never writes, spawns, fetches or calls a model.
 // Claude Code releases before mods ignore the `modules` key and keep running the settings hooks.
 //
 // The mods loader only follows `$` into functions declared at the top of this file, so each helper
@@ -10,8 +12,9 @@
 import { composeBand, composeEvidence } from "../lib/mod/frame.mjs";
 import { TIMINGS } from "../lib/mod/motion.mjs";
 import { renderBand, renderRows } from "../lib/mod/render.mjs";
-import { normalizeModSettings, resolveGlyphs } from "../lib/mod/settings.mjs";
-import { detectIconFont, readLedgerTail, readLitSnapshot } from "../lib/mod/state.mjs";
+import { accentFromSettings, normalizeModSettings, resolveGlyphs } from "../lib/mod/settings.mjs";
+import { chipStates, litSkillId, noteSkill } from "../lib/mod/skills.mjs";
+import { detectIconFont, readGitBranch, readLedgerTail, readLitSnapshot } from "../lib/mod/state.mjs";
 import { settledSample } from "../lib/mod/timeline.mjs";
 import {
   EMPTY_ACTIVITY,
@@ -19,7 +22,11 @@ import {
   buildEvidenceModel,
   detectCompletion,
   diffNotices,
+  mergeSpawned,
   noteAgentActivity,
+  noteSpawn,
+  noteSpawnActivity,
+  noteSpawnEnded,
   spinnerSuffix,
   trackAgents,
 } from "../lib/mod/view.mjs";
@@ -41,6 +48,7 @@ const createLive = (options) => ({
   snapshot: null,
   model: null,
   agents: [],
+  spawned: {},
   usage: null,
   activity: EMPTY_ACTIVITY,
   statusById: {},
@@ -55,6 +63,12 @@ const createLive = (options) => ({
   evidenceTab: "goal",
   ledger: [],
   celebrated: new Set(),
+  accent: undefined,
+  git: null,
+  fired: [],
+  settledAt: 0,
+  ignitionAt: undefined,
+  lastDiscipline: null,
 });
 
 const stateIo = ($) => ({
@@ -77,6 +91,9 @@ async function rebuild($, live) {
     isWorking: live.isWorking,
     notice: live.notice,
     completion: live.completion,
+    skills: chipStates(live.fired, live.settledAt),
+    lastDiscipline: live.lastDiscipline,
+    git: live.git,
   });
   live.model = next;
   if (previous?.visible && !next.visible && !live.exiting) {
@@ -112,20 +129,42 @@ function celebrate($, live, finish) {
   });
 }
 
+// A firing of a skill or command by name; anything that is not LitClaude's is ignored.
+async function noteFiring($, live, name) {
+  const id = litSkillId(name);
+  if (!id) return;
+  live.fired = noteSkill(live.fired, id, await $.clock.now());
+  live.lastDiscipline = id;
+  await rebuild($, live);
+}
+
+// The prompt hook rewrites the ignition record on every prompt; a new record naming a discipline is
+// a bare `lit` (or slash) routing, and lights that skill's chip at the time the hook wrote it.
+function noteIgnition(live, ignition, now) {
+  if (!ignition || ignition.at === live.ignitionAt) return;
+  live.ignitionAt = ignition.at;
+  live.lastDiscipline = ignition.discipline;
+  const id = litSkillId(ignition.discipline);
+  if (id) live.fired = noteSkill(live.fired, id, ignition.at ?? now);
+}
+
 async function refresh($, live) {
   if (live.refreshing) return;
   live.refreshing = true;
   try {
     const [cwd, sessionId] = await Promise.all([$.session.cwd(), $.session.id()]);
     const fresh = await readLitSnapshot(stateIo($), { cwd, sessionId, env: live.env });
-    live.agents = await $.agent.list().catch(() => []);
+    live.git = await readGitBranch(stateIo($), cwd).catch(() => live.git);
+    const listed = await $.agent.list().catch(() => []);
     live.usage = await $.session.usage().catch(() => live.usage);
     const now = await $.clock.now();
+    ({ agents: live.agents, spawned: live.spawned } = mergeSpawned(listed, live.spawned, now));
     live.activity = trackAgents(live.activity, live.agents, live.statusById, now);
     live.statusById = Object.fromEntries(live.agents.map((agent) => [agent.id, agent.status]));
     const before = live.snapshot;
     const previousModel = live.model;
     live.snapshot = fresh;
+    noteIgnition(live, fresh.ignition, now);
     const finish = detectCompletion(before, fresh);
     if (finish) celebrate($, live, finish);
     const next = await rebuild($, live);
@@ -167,6 +206,8 @@ export const register = (on, options) => {
       XDG_DATA_HOME: await $.env.get("XDG_DATA_HOME"),
       LOCALAPPDATA: await $.env.get("LOCALAPPDATA"),
     });
+    live.settledAt = await $.clock.now();
+    live.accent = accentFromSettings(await $.settings.read().catch(() => null), await $.env.get("LITCLAUDE_HUD_ACCENT"));
     await $.command.register({ name: PANE, description: "Show LitClaude goal criteria, evidence, lanes and gates in a pane" });
     await refresh($, live);
     $.clock.every(POLL_MS, () => {
@@ -182,7 +223,15 @@ export const register = (on, options) => {
   });
 
   on("turn.complete", async ($, e, next) => {
+    // A subagent's or teammate's turn ends its run, not the main turn the card follows.
+    if (typeof e.agentId === "string") {
+      live.spawned = noteSpawnEnded(live.spawned, e.agentId);
+      refreshSoon($, live);
+      return next(e);
+    }
     live.isWorking = false;
+    // The request is over: its chips dim to the recent list until a skill fires again.
+    live.settledAt = await $.clock.now();
     refreshSoon($, live);
     return next(e);
   });
@@ -194,12 +243,36 @@ export const register = (on, options) => {
   });
 
   on("tool.call", async ($, e, next) => {
+    if (e.tool === "Skill") await noteFiring($, live, e.skill);
+    if (typeof e.agentId === "string") live.spawned = noteSpawnActivity(live.spawned, e.agentId, await $.clock.now());
     const result = await next(e);
-    if (typeof e.agentId === "string") live.activity = noteAgentActivity(live.activity, e.agentId, await $.clock.now());
+    if (typeof e.agentId === "string") {
+      const now = await $.clock.now();
+      live.activity = noteAgentActivity(live.activity, e.agentId, now);
+      live.spawned = noteSpawnActivity(live.spawned, e.agentId, now);
+    }
     refreshSoon($, live);
     return result;
   }).catch(($, e, next) => next(e));
 
+  // Every subagent, teammate and workflow agent starts here. A workflow's never shows in
+  // `$.agent.list()`, so the card keeps its own record until the agent's turn.complete.
+  on("agent.spawn", async ($, e, next) => {
+    const result = await next(e);
+    if (typeof result?.agentId === "string") {
+      live.spawned = noteSpawn(live.spawned, { id: result.agentId, description: e.description, type: e.subagentType, at: await $.clock.now() });
+      refreshSoon($, live);
+    }
+    return result;
+  }).catch(($, e, next) => next(e));
+
+  // A typed `/litclaude:<name>` and the Skill tool both expand the skill's prompt here; the text
+  // passes through untouched.
+  on("skill.prompt", async ($, e, next) => {
+    await noteFiring($, live, e.skill);
+    return next(e);
+  }).catch(($, e, next) => next(e));
+
   on("ui.fault", async ($, e, next) => {
     if (e.component === "AbovePrompt") live.clientFailed = true;
     return next(e);
@@ -214,9 +287,9 @@ export const register = (on, options) => {
     const columns = Math.max(20, e.props.bodyColumns ?? e.viewport?.columns ?? 80);
     let drawn = null;
     if (elements.Client && !live.clientFailed) {
-      drawn = elements.Client({ key: "lit-band", module: "./lit-band-client.mjs", props: { model, columns, glyphs, motion: settings.motion } });
+      drawn = elements.Client({ key: "lit-band", module: "./lit-band-client.mjs", props: { model, columns, glyphs, motion: settings.motion, accent: live.accent } });
     } else if (model.visible) {
-      drawn = renderBand(elements, composeBand(model, settledSample(model), { columns, glyphs }));
+      drawn = renderBand(elements, composeBand(model, settledSample(model), { columns, glyphs, accent: live.accent }));
     }
     const below = await next(e);
     if (!drawn) return below;

package/plugins/litclaude/lib/canonical-skill-resources.mjs

@@ -11,8 +11,8 @@ export const canonicalSkillResourceManifest = Object.freeze(
     ["lib/durable-plan.mjs", "33fc7c2ba6305602c73650c8f29e6141e93b8ac32a444f772807e11bf8c22e44"],
     ["lib/immutable-expected-file-map.mjs", "4061486bc8eda8a53e56b7b346a1e400e7c858c0a682c83362fea460b46dfd4b"],
     ["lib/lit-mark.mjs", "cb57921a3da0ff983c74e9426dcd3b2379db090198743139e379a059c128021e"],
-    ["lib/office-runtime-lock/package-lock.json", "4b9552dba69bf2803cecdf71996d26de0497004c00d1e1f5753a5b299f85d8ba"],
-    ["lib/office-runtime-lock/package.json", "edf7fee2ba78d6ad42bf5761678b2a2210adb7282108864360f83c46adb59708"],
+    ["lib/office-runtime-lock/package-lock.json", "16d19b420b410035e9ca6886133368444a2b438121919857b3e8915be280c6a6"],
+    ["lib/office-runtime-lock/package.json", "5e4b0c7ee7bd5ff88c888f7f46152c605caf128cc4e7bfd16423571210925394"],
     ["lib/office-runtime-lock/requirements.lock", "7c63ce0de1ae9a912d1e546e9c01dd99a705d4a50435f36040d351cc3e6e6014"],
     ["lib/office-runtime.mjs", "24d108a4ae7aa98dd0d6f2fa66686d7c9f020ecf42fe641241be2869075bbea3"],
     ["lib/office_data.py", "0f4c2449622b6d59630e60508594d181279052c41918df4370e11a68df1ee239"],
@@ -848,11 +848,11 @@ export const canonicalSkillResourceManifest = Object.freeze(
     ["skills/readme-studio/templates/cover-source.json", "182051737e4cda9002360316bb2c01b500ecc20c27953a2d332d908f044f5cd7"],
     ["skills/readme-studio/templates/hyperframes-cover/index.html", "edaee52e01cc7d90524b43e3da80b4bc6514fef1d17b4317cbf15ed5e36a5c67"],
     ["skills/readme-studio/templates/hyperframes-cover/index.motion.json", "bef879ce5abe7810d73cc733ab635884ec807eccd7bc5e1c9bc9900049187249"],
-    ["skills/readme-studio/templates/hyperframes-cover/package-lock.json", "facce3fcbba7b9b5cd5b368b78192b035663a7c957f7802f97f037497dc193be"],
+    ["skills/readme-studio/templates/hyperframes-cover/package-lock.json", "5adacd09e4608c8c3917ca0245052e4d3abae3a566ebe07a2fdad593c67cb91c"],
     ["skills/readme-studio/templates/hyperframes-cover/package.json", "0993c6f04892f5a318cc99030de653b7c68d3ea6789c69b30b6a2ae80e4120f0"],
     ["skills/readme-studio/templates/readme-cover-section.md", "1dc4c536f65d3437f12e09a76170a8dc76557225587c7453631a06604a21573d"],
     ["skills/readme-studio/templates/readme-facts.json", "fb95b8aece0e8591726d3a36e25cc66712b0c6e57835c848db0f07b745e73205"],
-    ["skills/readme-studio/templates/remotion-cover/package-lock.json", "45cae4a5acee8bc98ef449a2ae91c4eae775afe7fc94769b86017bedb9301511"],
+    ["skills/readme-studio/templates/remotion-cover/package-lock.json", "422af74482c6c36e5bfaa86c2fe6a78e7ff54d27d3119f9c462685333a449857"],
     ["skills/readme-studio/templates/remotion-cover/package.json", "7921a415cf96343b46c9a2a3bea9160ecc807710fb6a34ba227704eff7d83887"],
     ["skills/readme-studio/templates/remotion-cover/src/index.tsx", "81cf3edd996a98ddca46465d4bc84ca0203ecd3bdce1736bf1dc3d9f2bc15af9"],
     ["skills/readme-studio/templates/typography/package-lock.json", "1d6dc1ae0d06d0a3a5e1b2b45bea1d40be7497f1f2fb856eefd33cc3649af5bd"],

package/plugins/litclaude/lib/hud-ignition.mjs

@@ -1,18 +1,13 @@
-import { existsSync, mkdirSync, readFileSync, renameSync, writeFileSync } from "node:fs";
+import { mkdirSync, renameSync, writeFileSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
 
-// Per-session ignition record: the prompt hook writes it on every UserPromptSubmit and the HUD
-// status line reads it back, so the status bar reflects the discipline actually selected for
-// the current turn instead of anything the model chooses to draw. Mode is per turn and never
-// durable, so the record lives in the per-user temp directory: not in the repository state
-// root (activation must stay side-effect-free there) and not in the home directory.
-
-const IGNITION_PALETTE = Object.freeze({
-  truecolor: "\x1b[38;2;255;99;55m",
-  "256": "\x1b[38;5;203m",
-  "16": "\x1b[91m",
-});
+// Per-session ignition record: the prompt hook writes it on every UserPromptSubmit and the LIT
+// card (hooks/lit-mod.mjs, through lib/mod/state.mjs) reads it back, so the card reflects the
+// discipline actually selected for the current turn instead of anything the model chooses to
+// draw. Mode is per turn and never durable, so the record lives in the per-user temp directory:
+// not in the repository state root (activation must stay side-effect-free there) and not in the
+// home directory.
 
 export const ignitionStateRoot = (env = process.env) => {
   const override = env.LITCLAUDE_HUD_STATE_ROOT?.trim();
@@ -47,28 +42,3 @@ export function writeIgnitionState({ sessionId, discipline }, env = process.env,
   renameSync(staging, target);
   return record;
 }
-
-export function readIgnitionState(sessionId, env = process.env) {
-  const target = ignitionStatePath(sessionId, env);
-  if (!existsSync(target)) return null;
-  try {
-    const parsed = JSON.parse(readFileSync(target, "utf8"));
-    if (!parsed || typeof parsed !== "object") return null;
-    return {
-      sessionId: typeof parsed.sessionId === "string" ? parsed.sessionId : null,
-      discipline: typeof parsed.discipline === "string" && parsed.discipline ? parsed.discipline : null,
-      at: typeof parsed.at === "string" ? parsed.at : null,
-    };
-  } catch {
-    return null;
-  }
-}
-
-export function renderIgnitionSegment(state, { depth = "plain" } = {}) {
-  const discipline = state?.discipline ?? null;
-  if (!discipline) return "";
-  const label = ignitionMark(discipline);
-  if (depth === "plain") return label;
-  const paint = IGNITION_PALETTE[depth] ?? IGNITION_PALETTE["256"];
-  return `\x1b[1m${paint}${label}\x1b[0m`;
-}