claude-token-saver 2.13.1 → 2.13.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.en.md +22 -6
  2. package/README.md +22 -6
  3. package/package.json +3 -3
package/README.en.md CHANGED
@@ -1,6 +1,6 @@
1
1
  [한국어](./README.md) · **English**
2
2
 
3
- [![DeepPulse YouTube](https://img.shields.io/badge/YouTube-@deeppulse-FF0000?logo=youtube&logoColor=white)](https://www.youtube.com/@deeppulse)
3
+ [![DeepPulse YouTube](https://img.shields.io/badge/YouTube-@DeepPulseKR-FF0000?logo=youtube&logoColor=white)](https://www.youtube.com/@DeepPulseKR)
4
4
  [![npm](https://img.shields.io/npm/v/claude-token-saver.svg)](https://www.npmjs.com/package/claude-token-saver)
5
5
 
6
6
  # claude-token-saver
@@ -13,11 +13,11 @@ A CLI to **diagnose and save tokens on Claude Code**. Cache hit rate, TTL countd
13
13
 
14
14
  📺 [Launch Short (60s)](https://www.youtube.com/shorts/RaD8qMsPTnA)
15
15
 
16
- ## Real-world impact — harness 5/5 + ratchet adoption
16
+ ## Cost-savings report — harness + ratchet adoption
17
17
 
18
- ![claude-token-saver before/after](./docs/harness-impact.png)
18
+ ![claude-token-saver — harness + ratchet adoption impact](./docs/harness-impact.png)
19
19
 
20
- Author's own Claude Code logs, normalized **per user message**, before/after adopting harness rules on 2026-05-02 (Opus 4.7 pricing):
20
+ The recently added **harness 5/5 + ratchet** features applied to the author's own Claude Code work, normalized **per user message** (cutoff 2026-05-02, Opus 4.7 pricing):
21
21
 
22
22
  | metric | before (7d / 739 msgs) | after (2d / 157 msgs) | Δ |
23
23
  |---|---:|---:|---:|
@@ -26,7 +26,17 @@ Author's own Claude Code logs, normalized **per user message**, before/after ado
26
26
  | assistant turns / user message | 9.73 | 8.83 | −9.2% |
27
27
  | tool calls / user message | 5.72 | 5.25 | −8.2% |
28
28
 
29
- > ⚠️ **Sample caveats** — POST window is only 2 days (157 msgs); statistical confidence is low. The work topic mix differs week to week (PRE week was video-script production with long pasted text, POST week was package release with short directives), so the tool/harness effect is not cleanly isolated. Refresh planned around **2026-05-09** once 5 more days of POST data are in.
29
+ Same request resolved in fewer round-trips → first-try success rate up. Looks like the effect of PEV + Structured Task forcing one-shot delivery.
30
+
31
+ ### Why cache hit rate isn't in this measurement — Max vs Pro
32
+
33
+ **Cache hit rate improvement isn't included** in this comparison. The author is on the Max plan with a 1-hour cache TTL and stays inside the same context for the full hour, so the hit rate had already converged near ~98% with little headroom left. **Pro-plan users (5-minute TTL)** see caches expire frequently, so the harness "one-shot" pattern + a "handoff right before TTL expiry" workflow likely **lifts hit rate itself**.
34
+
35
+ ### Handoff-before-expiry workflow
36
+
37
+ Watching the TTL countdown in the statusline, the habit is now: just before expiry, run `claude-token-saver handoff` to dump current work state into a markdown brief, then start a fresh cache cycle. Same flow handles the 1M-context warning and 5H/7D cap chips.
38
+
39
+ > ⚠️ **Sample caveats** — POST window is only 2 days (157 msgs); statistical confidence is low. The work topic mix differs week to week (PRE was video-script production with long pasted text, POST was package release with short directives), so the tool/harness effect isn't cleanly isolated. **Once 5 more days of POST data are in (around 2026-05-09)**, the same analysis will be re-run to check whether the trend stabilises, and an update will be posted.
30
40
 
31
41
  ---
32
42
 
@@ -246,7 +256,7 @@ Node.js ≥ 18 · macOS / Windows / Linux / WSL · zero dependencies.
246
256
 
247
257
  - [GitHub Issue #46829](https://github.com/anthropics/claude-code/issues/46829) — cache TTL regression
248
258
  - [HN discussion](https://news.ycombinator.com/item?id=47736476) — 168 points, 142 comments
249
- - [HNPulse KR](https://www.youtube.com/@HNPulseKR) — Korean HN tech deep-dives
259
+ - [HNPulse KR](https://www.youtube.com/@DeepPulseKR) — Korean HN tech deep-dives
250
260
 
251
261
  ## Known environment quirks
252
262
 
@@ -254,6 +264,12 @@ Node.js ≥ 18 · macOS / Windows / Linux / WSL · zero dependencies.
254
264
 
255
265
  ## Release notes
256
266
 
267
+ ### v2.13.3 (2026-05-04)
268
+ - "Real-world impact" section restructured as a **harness + ratchet adoption cost-savings report**. Added Max(1h)/Pro(5m) cache TTL distinction (different hit-rate headroom), the handoff-before-expiry workflow, and the 2026-05-09 refresh promise. Chart title updated to match.
269
+
270
+ ### v2.13.2 (2026-05-04)
271
+ - YouTube channel handle corrected to `@DeepPulseKR` (package.json + both READMEs).
272
+
257
273
  ### v2.13.1 (2026-05-04)
258
274
  - README now opens with the actual statusline screenshot and a "harness 5/5 + ratchet — before/after" impact chart, with daily/monthly/yearly cost-savings impact card. Author's own logs show −18.6% cost / user message, −9.2% assistant turns. Sample caveats, work-topic confound, and refresh schedule (2026-05-09) called out.
259
275
  - npm package metadata cleaned up (homepage / bugs / author) — package page now links to the DeepPulse YouTube channel.
package/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  **한국어** · [English](./README.en.md)
2
2
 
3
- [![DeepPulse YouTube](https://img.shields.io/badge/YouTube-@deeppulse-FF0000?logo=youtube&logoColor=white)](https://www.youtube.com/@deeppulse)
3
+ [![DeepPulse YouTube](https://img.shields.io/badge/YouTube-@DeepPulseKR-FF0000?logo=youtube&logoColor=white)](https://www.youtube.com/@DeepPulseKR)
4
4
  [![npm](https://img.shields.io/npm/v/claude-token-saver.svg)](https://www.npmjs.com/package/claude-token-saver)
5
5
 
6
6
  # claude-token-saver
@@ -13,20 +13,30 @@ Claude Code의 **토큰 사용량을 진단·절약**하는 CLI. 캐시 히트
13
13
 
14
14
  📺 [출시 영상 (60초)](https://www.youtube.com/shorts/RaD8qMsPTnA)
15
15
 
16
- ## 실제 효과 — harness 5/5 + ratchet 적용 전후
16
+ ## 실제 효과 — harness + ratchet 도입 전후 비용 절감 리포트
17
17
 
18
- ![claude-token-saver 설치 전/후 효과](./docs/harness-impact.png)
18
+ ![claude-token-saver — harness + ratchet 도입 효과](./docs/harness-impact.png)
19
19
 
20
- 저자 본인의 Claude Code 사용 로그를 **사용자 메시지 1건당**으로 정규화해 비교한 결과 (2026-05-02 적용 시점, Opus 4.7 가격 기준):
20
+ claude-token-saver에 최근 추가된 **harness 5/5 + ratchet** 기능을 실제 적용해보고 도입 전후를 비교한 결과입니다 (저자 본인의 Claude Code 사용 로그, **사용자 메시지 1건당**으로 정규화, 2026-05-02 기준, Opus 4.7 가격):
21
21
 
22
- | 메트릭 | 설치 전 (7일 / 739msg) | 설치 후 (2일 / 157msg) | 변화 |
22
+ | 메트릭 | 도입 전 (7일 / 739msg) | 도입 후 (2일 / 157msg) | 변화 |
23
23
  |---|---:|---:|---:|
24
24
  | 메시지당 비용 | $2.345 | $1.910 | **−18.6%** |
25
25
  | 메시지당 출력 토큰 | 7,391 | 6,052 | −18.1% |
26
26
  | 메시지당 assistant 왕복 | 9.73 | 8.83 | −9.2% |
27
27
  | 메시지당 도구 호출 | 5.72 | 5.25 | −8.2% |
28
28
 
29
- > ⚠️ **샘플 주의** — POST 데이터는 2일치(157 msgs)로 통계적 의미가 약하고, 그 주에 무슨 작업을 했냐(긴 텍스트 vs 짧은 지시)가 결과에 섞여 있습니다. 5일치가 더 쌓이는 **2026-05-09경** 같은 분석을 다시 돌려 갱신할 예정입니다.
29
+ 같은 요청을 더 적은 왕복으로 끝낸다 = 첫 시도 적중률 ↑. PEV·Structured Task가 강제로 한 번에 가게 만든 효과로 보입니다.
30
+
31
+ ### 캐시 히트율은 왜 이번 측정에 없는가 — Pro 플랜과의 차이
32
+
33
+ 이번 비교에는 **캐시 히트율 개선**이 포함되지 않았습니다. 저자는 Max 플랜이라 캐시 TTL이 1시간이고, 1시간 내내 같은 컨텍스트를 유지하며 작업해서 히트율이 이미 ~98%에 수렴해 있어 추가 개선 여지가 작습니다. **Pro 플랜 사용자(5분 TTL)는 캐시가 자주 만료되기 때문에**, harness가 만든 "한 번에 가는" 패턴 + 만료 직전 handoff 워크플로 조합으로 **히트율 자체가 올라갈 가능성이 큽니다.**
34
+
35
+ ### 만료 직전 handoff 워크플로
36
+
37
+ statusline에 TTL이 카운트다운되는 걸 보면서, 만료 직전에 `claude-token-saver handoff`로 현재 작업 상태를 마크다운으로 백업해두고 새 캐시 사이클을 시작하는 흐름이 자리잡았습니다. 1M 컨텍스트 경고나 5H/7D cap 칩이 떠도 같은 흐름으로 처리합니다.
38
+
39
+ > ⚠️ **샘플 주의** — 도입 후 데이터는 2일치(157 msgs)로 통계적 의미가 약하고, 그 주에 무슨 작업을 했냐(긴 텍스트 vs 짧은 지시)가 결과에 섞여 있어 도구 효과만 깨끗이 분리되진 않습니다. **총 7일치(추가 5일)가 쌓이는 2026-05-09경** 같은 분석을 다시 돌려 추세 안정화 여부와 함께 갱신할 예정입니다.
30
40
 
31
41
  ---
32
42
 
@@ -214,6 +224,12 @@ Node.js ≥ 18 · macOS / Linux / Windows / WSL · 의존성 0.
214
224
 
215
225
  ## 릴리스 노트
216
226
 
227
+ ### v2.13.3 (2026-05-04)
228
+ - "실제 효과" 섹션을 **harness + ratchet 도입 전후 비용 절감 리포트** 형태로 재구성. Max(1h)/Pro(5m) 캐시 TTL 차이에 따른 히트율 개선 여지 차이 설명, 만료 직전 handoff 워크플로 안내, 7일치 누적 시점(2026-05-09) 갱신 예고 추가. 차트 제목도 동일하게 갱신.
229
+
230
+ ### v2.13.2 (2026-05-04)
231
+ - YouTube 채널 핸들 `@DeepPulseKR`로 정정 (package.json + 두 README 일괄).
232
+
217
233
  ### v2.13.1 (2026-05-04)
218
234
  - README에 실제 statusline 스크린샷과 "harness 5/5 + ratchet 적용 전후 효과" 차트 추가. 자체 사용 로그 기준 메시지당 비용 −18.6%, assistant 왕복 −9.2%, 일/월/년 환산 비용 절감 임팩트 카드 포함. 샘플 주의사항·작업 토픽 변수·갱신 일정(2026-05-09) 명시.
219
235
  - npm 패키지 메타데이터(homepage / bugs / author) 정비 — DeepPulse YouTube 채널 링크 노출.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "claude-token-saver",
3
- "version": "2.13.1",
3
+ "version": "2.13.3",
4
4
  "description": "Save tokens on Claude Code — spike diagnosis, 1M-context detection, TTL countdown, statusline. (formerly claude-cache-monitor)",
5
5
  "type": "module",
6
6
  "bin": {
@@ -37,9 +37,9 @@
37
37
  "type": "git",
38
38
  "url": "git+https://github.com/rootstudioyaml/claude-token-saver.git"
39
39
  },
40
- "homepage": "https://www.youtube.com/@deeppulse",
40
+ "homepage": "https://www.youtube.com/@DeepPulseKR",
41
41
  "bugs": {
42
42
  "url": "https://github.com/rootstudioyaml/claude-token-saver/issues"
43
43
  },
44
- "author": "DeepPulse (https://www.youtube.com/@deeppulse)"
44
+ "author": "DeepPulse (https://www.youtube.com/@DeepPulseKR)"
45
45
  }