Write a coding agent from first principles: better tools
This tutorial builds on the coding agent you implemented in the tutorial “Write a coding agent from first principles”. In this tutorial, you'll take your agent and improve its capabilities by implementing the text edit and bash command tools that Anthropic provides.
mathspp.com/blog/write-a-c…
You shouldn't trust Trusted Publishing
The post explains that PyPI Trusted Publishing is an authentication mechanism for machine-to-machine trust between CI/CD workflows and package registries, not a signal that a package is safe or high quality. It shows how Trusted Publishing reduces long-lived credential risk, while warning that users should not treat it like a “green checkmark” because malicious or low-quality packages ca...
blog.yossarian.net/2026/07/07/You…
bradautomates / claude-video
Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
github.com/bradautomates/…
microsoft / SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
github.com/microsoft/Skil…
How to publish to PyPI using GitHub Actions securely
The post gives three practical steps for publishing Python packages to PyPI more securely from GitHub Actions: run zizmor, use Trusted Publishing, and require manual approval through GitHub environments. It focuses on reducing credential risk by removing long-lived PyPI tokens, pinning actions, limiting workflow permissions, disabling persisted checkout credentials, and adding a human ap...
snarky.ca/how-to-publish…
Serving a Frontend with FastAPI: A Practical Guide
A practical guide to FastAPI's new app.frontend(), SPA fallback, API route priority, and a complete mini dashboard example.
modernpython.io/serving-a-fron…
planning-with-files
Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.
github.com/OthmanAdi/plan…
Django security releases issued: 6.0.7 and 5.2.16
Django 6.0.7 and 5.2.16 fix three low-severity security issues involving cached Set-Cookie responses, GDALRaster heap buffer over-read, and DomainNameValidator accepting newlines. The Django team recommends upgrading supported versions as soon as possible, with patches applied to main, 6.1 beta, 6.0, and 5.2 branches.
djangoproject.com/weblog/2026/ju…
Have your agent record video demos of its work with shot-scraper video
shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which ...
#atom-tag" target="_blank" rel="nofollow noopener">simonwillison.net/2026/Jun/30/sh…