Bookmarks

Bookmarks

orchestrate — nine subagent orchestration strategies for AI coding agents
orchestrate — nine subagent orchestration strategies for AI coding agents
A Claude Code skill with nine subagent-orchestration strategies — staged, parallel, hierarchical, team, workflow, loop, advisor, adversarial, xcli — auto-triaged, gated, and resumable.
·orchestrate-skill.vercel.app·
orchestrate — nine subagent orchestration strategies for AI coding agents
redhat-et/ripwire: The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
redhat-et/ripwire: The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run,...
·github.com·
redhat-et/ripwire: The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
okf-memory/okf-agent-memory: Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
okf-memory/okf-agent-memory: Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with ...
·github.com·
okf-memory/okf-agent-memory: Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Dotfiles That Save Themselves
Dotfiles That Save Themselves
Track the configuration you already use, recover mistakes, and bring your setup to another machine with mise.
·jdx.dev·
Dotfiles That Save Themselves
mathiswrong/Things-MCP: MCP server for Things 3 on macOS. Manage tasks, projects, tags, checklists, reminders and templates through supported automation, with verified project move summaries.
mathiswrong/Things-MCP: MCP server for Things 3 on macOS. Manage tasks, projects, tags, checklists, reminders and templates through supported automation, with verified project move summaries.
MCP server for Things 3 on macOS. Manage tasks, projects, tags, checklists, reminders and templates through supported automation, with verified project move summaries. - mathiswrong/Things-MCP
·github.com·
mathiswrong/Things-MCP: MCP server for Things 3 on macOS. Manage tasks, projects, tags, checklists, reminders and templates through supported automation, with verified project move summaries.
Andrei Rebrov on X: "My biggest recent discovery - @herdrdev. This is wow I run 25 AI coding agents like a team, not a chatroom. 1/ I run ~25 coding agents across 5 harnesses (Claude Code, Codex, opencode/GLM, Grok, agy) from one terminal console (herdr). Each agent has a role — coder, reviewer, https://t.co/DjeGxugXxK" / X
Andrei Rebrov on X: "My biggest recent discovery - @herdrdev. This is wow I run 25 AI coding agents like a team, not a chatroom. 1/ I run ~25 coding agents across 5 harnesses (Claude Code, Codex, opencode/GLM, Grok, agy) from one terminal console (herdr). Each agent has a role — coder, reviewer, https://t.co/DjeGxugXxK" / X
This is wow I run 25 AI coding agents like a team, not a chatroom. 1/ I run ~25 coding agents across 5 harnesses (Claude Code, Codex, opencode/GLM, Grok, agy) from one terminal console (herdr). Each agent has a role — coder, reviewer, judge, design, PM, SR…
·x.com·
Andrei Rebrov on X: "My biggest recent discovery - @herdrdev. This is wow I run 25 AI coding agents like a team, not a chatroom. 1/ I run ~25 coding agents across 5 harnesses (Claude Code, Codex, opencode/GLM, Grok, agy) from one terminal console (herdr). Each agent has a role — coder, reviewer, https://t.co/DjeGxugXxK" / X
hey-api/hey-api: 👨‍🚀 Turn API specifications into production-ready SDKs, validators, mocks, and more. 20+ plugins. Millions of weekly npm downloads. Used by Vercel, OpenCode, PayPal, AWS, Autodesk, and many more.
hey-api/hey-api: 👨‍🚀 Turn API specifications into production-ready SDKs, validators, mocks, and more. 20+ plugins. Millions of weekly npm downloads. Used by Vercel, OpenCode, PayPal, AWS, Autodesk, and many more.
👨‍🚀 Turn API specifications into production-ready SDKs, validators, mocks, and more. 20+ plugins. Millions of weekly npm downloads. Used by Vercel, OpenCode, PayPal, AWS, Autodesk, and many more. -...
·github.com·
hey-api/hey-api: 👨‍🚀 Turn API specifications into production-ready SDKs, validators, mocks, and more. 20+ plugins. Millions of weekly npm downloads. Used by Vercel, OpenCode, PayPal, AWS, Autodesk, and many more.
koyasi777/mozkey: Mozc(Google日本語入力)をベースに、遅延付きライブ変換・ローカル Zenz 補正・ダークテーマ対応・句読点単打確定・学習ロジックの改善・文脈を見た変換補正などを統合した、ローカルファーストな日本語入力 fork です。
koyasi777/mozkey: Mozc(Google日本語入力)をベースに、遅延付きライブ変換・ローカル Zenz 補正・ダークテーマ対応・句読点単打確定・学習ロジックの改善・文脈を見た変換補正などを統合した、ローカルファーストな日本語入力 fork です。
Mozc(Google日本語入力)をベースに、遅延付きライブ変換・ローカル Zenz 補正・ダークテーマ対応・句読点単打確定・学習ロジックの改善・文脈を見た変換補正などを統合した、ローカルファーストな日本語入力 fork です。 - koyasi777/mozkey
·github.com·
koyasi777/mozkey: Mozc(Google日本語入力)をベースに、遅延付きライブ変換・ローカル Zenz 補正・ダークテーマ対応・句読点単打確定・学習ロジックの改善・文脈を見た変換補正などを統合した、ローカルファーストな日本語入力 fork です。
フォームの Enter 送信で isComposing と keyCode === 229 を併用する理由
フォームの Enter 送信で isComposing と keyCode === 229 を併用する理由
IME の変換確定に使う Enter キーで、書きかけのメッセージが送信されることがあります。isComposing と非推奨の keyCode === 229 を併用して、変換中の Enter を送信処理から除外する理由を解説します。
·azukiazusa.dev·
フォームの Enter 送信で isComposing と keyCode === 229 を併用する理由
Grillingで詰まったら、推測せず分岐する - Algomatic Tech Blog
Grillingで詰まったら、推測せず分岐する - Algomatic Tech Blog
こんにちは。AlgomaticでソフトウェアエンジニアをしているGo(@53able)です。 mattpocock/skillsは、開発作業の進め方をエージェントに教えるスキル集です。 github.com /grillingは、その中で曖昧な依頼から未決定事項と判断の依存関係を洗い出す役割を担います。未決定事項を掘り…
·tech.algomatic.jp·
Grillingで詰まったら、推測せず分岐する - Algomatic Tech Blog
バックエンド開発Handbookを届けるために ― AI時代の知の高速道路を敷く - Timee Product Team Blog
バックエンド開発Handbookを届けるために ― AI時代の知の高速道路を敷く - Timee Product Team Blog
こんにちは、タイミーでバックエンドのテックリードをしている新谷(@euglena1215)です。 今回は、社内向けに公開したバックエンド開発Handbookと、それをClaude CodeやCursorといったAIエージェント向けスキルとして届けることで、気づいたらHandbookを参照している状態を目指した取り組みに…
·tech.timee.co.jp·
バックエンド開発Handbookを届けるために ― AI時代の知の高速道路を敷く - Timee Product Team Blog
GitHub ActionsでCodeRabbit to Humanになるようレビューフローをコントロールする - プププなテクブ
GitHub ActionsでCodeRabbit to Humanになるようレビューフローをコントロールする - プププなテクブ
このブログは以下のブログの続編です。 blog.inorinrinrin.com 以前のブログではCodeRabbit以外のレビューエージェントでもAI to Humanの流れを踏むように、"ReviewReady"のようなラベルをトリガーすることで人間のレビュアーを割り当てる仕組みを紹介しました。 しかし、最近はCo…
·blog.inorinrinrin.com·
GitHub ActionsでCodeRabbit to Humanになるようレビューフローをコントロールする - プププなテクブ
Bet AI Day 2026丨How We Bet AI: AIとともに働く場をつくる
Bet AI Day 2026丨How We Bet AI: AIとともに働く場をつくる
2026年9月3日に開催されたイベント「Bet AI Day 2026」における登壇資料です。 ■ 概要 世はまさに大AIエージェント時代!!!私たちは、プロダクトを通したAIエージェントの社会実装と、社内利用を通した私たち自身への実装を両面で進めています。この発表では、主に社内利用のためのプラ…
·speakerdeck.com·
Bet AI Day 2026丨How We Bet AI: AIとともに働く場をつくる
Maybe We Shouldn't Be Reviewing All This Code
Maybe We Shouldn't Be Reviewing All This Code
Or, perhaps the problem isn't that AI has broken code review, maybe it’s that we've been using code review to solve the wrong problems
·martinfowler.com·
Maybe We Shouldn't Be Reviewing All This Code
Changes to SourceHut's terms of service regarding LLMs
Changes to SourceHut's terms of service regarding LLMs
sourcehut is a network of useful open source tools for software project maintainers and collaborators, including git repos, bug tracking, continuous integration, and mailing lists.
·sourcehut.org·
Changes to SourceHut's terms of service regarding LLMs