Fetching from the wire…
01
02
03
04
05
06
07
08
OSS2026-08-21 · source-backed
One Python file wiring a model to exactly one tool, bash, with the system prompt loaded from a file the agent can rewrite. Tools, memory, skills, conventions all have to be grown by the agent session by session into a self/ directory that persists. Model access goes through Simon Willison's llm library. GitHub 40 stars, a research toy rather than a harness. The question it poses is genuinely interesting: what does an agent actually reinvent when you give it nothing?
Each link below shares sources, entities, or timing with this story.
The Claude Code source leak was the biggest story in developer tools this week. But the most important analysis didn't come from the people picking through feature flags and Easter eggs. It came from Sebastian Raschka, who read the 512,000 lines of leaked TypeScript and reache...
Simon Willison released it August 4, calling it "the most significant new version since the initial launch of the project," which from him is not marketing. The agent-relevant pieces: tools can raise llm.PauseChain to stop for human approval, and chains resume from pending cal...
headroomlabs-ai/headroom at 62.5K stars sits between an agent and its LLM compressing tool outputs, logs, files, and RAG chunks in flight, claiming 20% fewer tokens for coding agents and 60-95% fewer for JSON at unchanged answer quality (GitHub). Six content-type-specific comp...
Check Point Research disclosed CVE-2025-59536 and CVE-2026-21852 — two vulnerabilities that weaponize Claude Code's project configuration system against its users. This matters because an Agents Anonymous survey this week showed 90% of practitioners at their SF meetup use Clau...
GPT-5.6 Luna went to $0.20 input / $1.20 output per million tokens on July 30. That's an 80% cut. Terra dropped 20%. Luna's input now undercuts Gemini 3.1 Flash-Lite ($0.25/$1.50) and sits at one-fifth of Claude Haiku 4.5's $1 input. Simon Willison covered the announcement and...
If you've written Claude Code skills with context: fork in the frontmatter, go check them right now. As of the July 22 release, /code-review runs as a background subagent, and any skill declaring context: fork runs in the background by default (release notes). The opt-out is b...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.