Full-text search across 59512 articles. Combine with topic and date filters; results sorted by relevance.
A developer released Keep the Why, an open-source tool that stores project rationale as Markdown files under a `context/` directory in Git so coding agents consult prior decisions before proposing changes. In a controlle…
A developer argues that stale agent instruction files like AGENTS.md are more dangerous than missing rules because they make coding agents confidently follow outdated commands, and proposes a CI doc-drift check that comp…
GitHub announced an AI detector built with Microsoft Applied Sciences that expands its push protection to catch unstructured secrets, such as database passwords, before they enter repository history. The ModernBERT-based…
A developer outlined a dual-prompt pattern for coding-agent tasks that splits a single long prompt into a precise implementation brief and a shorter supervision brief, separating what the agent executes from who judges a…
A developer at Driftproof ran the same Claude Code git-workflow skill on Claude Haiku 5.5 three times and found the measured benefit swung from +0.549 to -0.010 to +0.235, with the skill arm holding steady near 0.84 whil…
A developer documented how Claude Code, Codex, and Grok Build each prevent Mac idle sleep only while an agent turn is actively running, releasing the assertion between turns and while waiting for user approval. The write…
The MonkeysCode team shipped two infrastructure updates to its context kernel and model proxy to harden autonomous coding agents against dropped SSE streams and prompt-cache misses. The proxy now injects SSE comment ping…
A developer documented how to add a side pane to Claude Code using a mod, showing that a pane must be opened with $.ui.open({ id }) and its contents returned from a ui.render handler matching { component: 'Pane' } on the…
A QA engineer who runs the Devin coding agent daily built a suite of twenty local-first tools that verify an agent's claims against its own on-disk telemetry rather than its narrative, after a session reported "fixed, al…
A developer released quota-audit v1.3.0, an open-source Claude Code plugin that parses the per-message token usage already written into local session transcripts under ~/.claude/projects/*/*.jsonl to break usage down by …
Google announced Gemini 4 Argon, a frontier AI model it says scores 68.9 percent on Vals knowledge-work benchmark versus 63.1 percent for GPT-6 Astra and 65.8 percent for Claude Fable 5.1, and 91.9 percent on Vibe Code B…
A developer who works with coding agents on long autonomous tasks has documented an anti-pattern called a "proof spiral," in which an agent writes checks of its checks — building receipt checkers, fingerprints and proven…
Google DeepMind introduced Gemini 4 Argon, a frontier model for long-horizon coding, enterprise knowledge work, and cyber defense that sets a state of the art of 77.9% on DeepSWE v1.1 and raises the output limit from 64K…
A developer built GODMODE V3, an authority and policy layer for Claude Code that moves agent guardrails out of the system prompt and into a PreToolUse hook that can deny any mutating tool call. The gate requires a live V…
Two developers who previously worked at several business-intelligence companies released Graphene, an open-source data analysis toolkit that gives coding agents a semantic layer, MDX-like dashboard files, and connectors …
A developer built Jancera/skills, a set of skills and subagents for Google Antigravity that keeps a human in the loop on multi-agent coding work by auto-approving read-only commands, sandboxing implementation agents at t…
Developer dlhck released Ferry, an open-source tool that syncs coding agent setups — skills, instructions, MCP servers and supported settings — from a local machine to remote Linux boxes via a private git snapshot reposi…
A developer built cliffhanger, an open-source Stop hook and skill for Claude Code that blocks the agent from ending a turn while checklist items remain open, allowing a real stop only for named blockers, background tasks…
Microsoft released Visual Studio Code 1.141 (Insiders) on September 30, 2026, adding a "Chat: Clean Up Agent Worktrees" command that lets users review and remove inactive agent worktrees. The release notes, generated wit…
A developer published a selection framework for choosing between OpenAI's GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Astra for coding agents, comparing API IDs, Standard pricing, caching rates, context limits, and endpoint suppor…