worklore.dev · all stories · authors · paths · skills & mcp · about
home / claude-code
tools and agents · 13 stories
claude-code
Working inside Claude Code: skills, hooks, memory, token cost, and the habits that make a long session hold together.
- Cut Claude Code token cost 4×: let your MCP tool take a URL instead of the pasted file
When an agent gives a tool a long piece of text, the model usually types that text out again as the tool's argument.
Yahhi✓ 0 - Benchmark your MCP server in Claude Code, Codex and Gemini: one fake server, its call log as the judge
In plain words: before you decide how many tools your MCP server should have, whether to group them, or how to name them, you can test the decision on the clients your users actually run, instead of…
Yahhi✓ 0 - Why my agent's shell commands kept failing on a Mac: 54 errors counted, then fixed
Plain version first: my coding agent writes shell commands for Linux, and my Mac is not Linux.
Yahhi✓ 0 - A morning brief in my inbox — my agent emails me my projects' pulse before I start
I juggle a few projects, and every morning — or after switching between them — I'd lose the thread: what's the state, what needs me today.
Yahhi✓ 0 - The Relay Board — my agent runs the GitHub kanban, I just close my cards
Building a connector with my agent, I kept losing the thread.
Yahhi✓ 0 - See what a skill can do before you run it — a stdlib capability scanner
An agent skill is text your agent executes with your permissions.
Yahhi✓ 0 - The 1-Page Marketing Plan as an agent skill — interview me, build the Sheet
I read Allan Dib's The 1-Page Marketing Plan and realized the only durable output of a whole business plan is that one 3×3 grid — nine squares across Before / During / After.
Yahhi✓ 0 - A stranger could "like" my private tasks — the access rule my API forgot
Plain version: an API bug where the app correctly stops you from seeing someone else's private thing, but forgets to stop you from touching it.
Yahhi✓ 0 - Half-remembered Mom Test — an agent skill turned fuzzy course notes into exact interview questions
In plain words: most of what we learn on courses degrades into a vague feeling of "there were rules about this."
Yahhi✓ 0 - Hand-writing a logo in SVG with an AI agent — no image generator needed
I needed a logo and did what everyone does now: opened an image generator.
Yahhi✓ 0 - A second AI opinion inside Claude Code — Gemini over curl, no arena apps
I work with one agent all day, and one agent means one set of blind spots.
Yahhi✓ 1 - Two bugs made my scheduler perfectly silent — zsh killed the messenger
Yesterday I filed an open failure: my launchd job — a daily 16:50 headless-agent review — produced nothing.
Yahhi✓ 0 - My launchd daily review never fired — no error, no output, nothing
RESOLVED 2026-08-01 — and my headline was wrong in the best way: the job HAD fired, both days, on schedule.
Yahhi✓ 0
agents: /t/claude-code.md