I use cape.el to manage specific completion-at-point functions.
The most used ones for me are {C-c t f} - complete file name and
{C-c t s} - complete Elisp symbol.
After starting using ghostel with Claude Code being able to complete
the buffer name became more desirable than ever, so I can quickly
drop into notes things like this:
(vux-ghostel-buffer "cape-buffer")
Asked Claude, it wrote "cape-buffer-name" function, bound to {C-c t b}. Works!
I was cleaning my screenshots directory and spotted one from the
"Wisey" service that teaches you mindfullness and habits. I didn't go
to subscribe to the service but I did save the screenshot.
I asked Claude Code: I want Graphviz graph that looks as close as
possible to this file:
And here's the result I got in a minute:
(vux-ghostel-buffer "graphviz-morning-routine")
Not bad, huh?
claude-pager
On <2026-06-03 Wed> I somehow bumped into idea to
use emacsclient as EDITOR in Claude Code.
Turns out CC respects EDITOR env variable, either from
environment or configured in ~/.claude/settings.json:
In that issue I spotted this project: gradigit/claude-pager. Fast C
transcript pager for Claude Code: no blank Ctrl-G screen, clickable
links/files, queued prompt composer. And its sister editor: gradigit/turbodraft.
Tried both. Turbodraft - I don't need another text editor rather than Emacs,
so skipping it. But claude-pager looks useful, so I forked it.
First, I wired Emacs into claude-pager; so that it renders transcripts
in both CC screen when it waits for the prompt + adds it to Emacs temporary
buffer.
This mostly solves clunkiness of copying from claude terminal into Emacs and
back - now I press {C-g} in claude and continue editing in Emacs.
{C-g} in claude opens claude-pager-open that generates transcript
and pastes it into both terminal and to the temp file to edit in Emacs,
then runs claude-emacs-prompt shell file that calls elisp file which
loads into the buffer, assigns keybindings etc.
Then I rewrote the binary from C to Zig. Rewrite used Superpowers to
develop a spec first, then launch a series of agents. It took 4+
hours for CC to finish rewrite, it was ready in the morning. It used
all extra usage (42 EUR) in fast mode in first 20 minutes.
7000 loc in C => ??? in Zig.
Now I understand the C well.
Another interesting project from the same author:
gradigit/confetti - Lightweight confetti animation for macOS — fire
colorful confetti from your screen corners
Copy buffer-name with easy-kill
easy-kill Emacs package allows killing multiple things, switching
between them on the fly. I use it to quickly grab the
buffer-file-name (full path or file name only), using {M-w b}.
In order for format-all picks up terraform-fmt formatter of Terraform files,
when using Tree Sitter with terraform-ts-mode, the mode should be registered
in language-id package like this:
To have fun with kids, I wrapped kids-unicode minor mode that brings
keymap redefining every key to insert emoji. Enable with {M-x
kids-unicode-mode} and have fun typing, encoding names with emojis and
train memory.
Below is the content of ~/.claude/skills/youtube-monitor/SKILL.md that
I fully wrote myself. You can see results by searching for YouTube
tag. I added a Claude Routine to run this skill daily. Let's see how
it would work.
---
name: youtube-monitor
description: Monitor and summarize new YouTube videos from channels I follow.
compatibility: Requires curl and network access.
allowed-tools: Bash WebSearch
---
## Instructions
### Step 1: Identify channells that I follow
Check `elfeed-feeds` variable in Emacs (via `emacsclient`), filter YouTube
channels.
### Step 2: Find latest videos using /youtube-finder skill
Exclude shorts.
### Step 3: Find new videos that were not yet summarized
Run this shell command, providing correct user handle of the channel:
```sh
cat ~/Notes/youtube_summaries.org | grep -E '(<handle>)' -A5 | head -n 10
```
In results will be the last summarized video, all videos after that are new.
### Step 4: Summarize each new video
Summarize each new video using /youtube-summarizer skill, write new
summary to ~/Notes/youtube_summaries.org file as the first heading,
using this template:
```org-mode
* <title of the video> – <name> (<handle>) YouTube
:PROPERTIES:
URL <url of the video>
DURATION <MM:SS>
PUBLISHED <YYYY-MM-DD DOW>
END
- <url of the video>
<abstract>
/summary generated by my "YouTube summarizer" AI skill./
<full summary, if using subheadings, only H2 are allowed>
```
claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@caveman
claude plugin uninstall caveman@caveman && claude plugin marketplace remove caveman
Uninstalled after reading HN comments. Installed again recently.
Caveman in gptel
Add caveman as a gptel directive:
(setq gptel-directives
(cons '(caveman . "CAVEMAN MODE: Drop articles/filler/pleasantries/hedging. Fragments OK. Short synonyms. Pattern: [thing] [action] [reason]. [next step]. Keep full technical accuracy. Code unchanged.")
gptel-directives))
Select with C-c C-d in gptel buffer.
HN comments summary
A developer created "Caveman," a Claude Code skill that forces the AI
to respond in simplified, caveman-like language to reduce token usage
by approximately 75%. The author clarifies this is mostly a joke and
targets visible output (removing preambles and filler text), not the
hidden "thinking" tokens that improve performance. They acknowledge
the ~75% claim needs proper benchmarking and note that the skill
doesn't affect code quality itself.
The Hacker News community is highly skeptical, with many arguing that
tokens are "units of thinking" for LLMs—reducing them could make the
model dumber by limiting its reasoning capacity. Critics point out
that chain-of-thought reasoning requires verbose output, and forcing
concise responses may degrade performance. However, some find the
concept useful for cutting through verbose AI responses, comparing it
to telegram-style communication or noting that similar concise
prompting can work without harming quality for simple tasks. The
debate centers on whether this actually saves meaningful costs versus
potentially sacrificing accuracy.
