@antonior/claude-code-setup 1.1.0 → 1.1.2
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.
- package/README.md +28 -4
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,9 +2,23 @@
|
|
|
2
2
|
|
|
3
3
|
[](https://www.npmjs.com/package/@antonior/claude-code-setup)
|
|
4
4
|
[](./LICENSE)
|
|
5
|
-
[](#
|
|
5
|
+
[](#platforms)
|
|
6
|
+
[](#optimised-for-low-token-usage)
|
|
6
7
|
|
|
7
|
-
One-command installer for my [Claude Code](https://claude.com/claude-code) configuration — hooks, slash commands, skills, statusline, and global rules. Install once, get the exact setup I use every day.
|
|
8
|
+
One-command installer for my [Claude Code](https://claude.com/claude-code) configuration — hooks, slash commands, skills, statusline, and global rules. Install once, get the exact setup I use every day. **Optimised for low token usage.**
|
|
9
|
+
|
|
10
|
+
## Why this setup?
|
|
11
|
+
|
|
12
|
+
Stock Claude Code is powerful but neutral. This config turns it into a careful, cost-aware engineer with guardrails — the difference between an assistant that *sounds* confident and one that *proves* its work.
|
|
13
|
+
|
|
14
|
+
- **🛡️ Trustworthy by default.** Built-in rules forbid the things that quietly burn you: never fakes or weakens tests, never suppresses errors with `@ts-ignore` / `eslint-disable` / swallowed `catch`, never claims "done" without verifying. Failures get surfaced, not hidden.
|
|
15
|
+
- **🔒 Catches mistakes before they ship.** `scan-secrets` blocks any commit containing API keys or a real `.env`. `stop-verify` runs lint + typecheck on the files you changed at the end of every turn and won't let "done" slide if they fail. `check-dep` forces a real look at any new dependency (size, maintenance, lighter alternatives) before it's added.
|
|
16
|
+
- **🎯 Stays in scope.** Only changes what you asked for — no drive-by refactors, no unrequested "improvements", no comments bolted onto code it didn't touch.
|
|
17
|
+
- **🧠 Remembers across sessions.** The `transcript-search` MCP indexes your *own* past conversations locally, so Claude recalls prior decisions ("like we did last time") instead of saying "I don't remember" — and instead of you re-explaining context.
|
|
18
|
+
- **💸 Cheap on tokens.** Caveman mode keeps full technical accuracy while cutting chatter ~75%; video defaults to audio-only transcription; verification hooks touch only changed files, not the whole repo. See [Optimised for low token usage](#optimised-for-low-token-usage).
|
|
19
|
+
- **🎬 Understands video.** The `claude-video-vision` MCP lets Claude watch and reason about video, not just text.
|
|
20
|
+
- **📊 Knows where you stand.** A rich statusline shows git branch + dirty state, model and effort level, context-window %, and your 5-hour / 7-day rate-limit usage at a glance.
|
|
21
|
+
- **⚡ Zero-friction, safe install.** One command installs everything, auto-installs its dependencies, registers the MCP servers, and **smart-merges** into any existing config (it never clobbers your `settings.json` or `CLAUDE.md`). Idempotent — re-run any time to pull updates.
|
|
8
22
|
|
|
9
23
|
## Install
|
|
10
24
|
|
|
@@ -14,9 +28,9 @@ npx @antonior/claude-code-setup
|
|
|
14
28
|
|
|
15
29
|
That's it. The installer is idempotent — safe to re-run to pull updates.
|
|
16
30
|
|
|
17
|
-
##
|
|
31
|
+
## Platforms
|
|
18
32
|
|
|
19
|
-
|
|
33
|
+
Built and tested on **macOS**. Linux and native Windows aren't officially supported yet — the hooks are bash and the installer uses Homebrew, so a full cross-platform pass is needed before I'd claim them.
|
|
20
34
|
|
|
21
35
|
## Dependencies (auto-installed via Homebrew)
|
|
22
36
|
|
|
@@ -52,6 +66,16 @@ Both are installed and auto-registered for you:
|
|
|
52
66
|
|
|
53
67
|
- **`transcript-search`** — full-text search over your *own* past Claude Code transcripts ("we talked about…", "like last time"). Pure-Python, stdlib only. The index is built **locally on your machine** from `~/.claude/projects/` on first run — nothing about your conversations is ever shipped in this package.
|
|
54
68
|
- **`claude-video-vision`** — lets Claude watch/analyse videos (frames via `ffmpeg`). Published as [`claude-video-vision`](https://www.npmjs.com/package/claude-video-vision) on npm; run via `npx`.
|
|
69
|
+
- **Tip:** when it asks how many FPS, answer **0** to use audio transcription only (no frame extraction) — much cheaper on tokens. Bump the FPS only when you actually need on-screen/visual detail.
|
|
70
|
+
|
|
71
|
+
## Optimised for low token usage
|
|
72
|
+
|
|
73
|
+
This setup is deliberately token-lean:
|
|
74
|
+
|
|
75
|
+
- **`/caveman` skill + caveman hook** — ultra-compressed replies that keep full technical accuracy while cutting chatter (~75% fewer tokens), with `lite`/`full`/`ultra` intensity levels.
|
|
76
|
+
- **Video → 0 FPS** — analyse video by audio transcription only unless you explicitly need visual frames, avoiding expensive frame tokens.
|
|
77
|
+
- **`transcript-search` over re-explaining** — recalls past decisions from your own history instead of re-deriving context.
|
|
78
|
+
- **Scoped, high-signal hooks** — `stop-verify` and `eslint-fix` only act on files you actually changed, not whole-repo sweeps.
|
|
55
79
|
|
|
56
80
|
## On a new machine — two one-time steps
|
|
57
81
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@antonior/claude-code-setup",
|
|
3
|
-
"version": "1.1.
|
|
3
|
+
"version": "1.1.2",
|
|
4
4
|
"description": "Install Antonio's full Claude Code setup: hooks, slash commands, skills, statusline, settings, and MCP servers (transcript-search + video-vision)",
|
|
5
5
|
"bin": {
|
|
6
6
|
"claude-code-setup": "bin/install.js"
|