#Tasks

KEEPING PROMISES. Ten days into leading the Barracks Task Force. This mission is personal. Grateful to @SecWar @PeteHegseth @DeptofWar and the Airmen at Moody Air Force Base. Our Service members kept their promise. Now we keep ours. I’m going to fix this. #BTF #BarracksTaskForce

Secretary of the Treasury Scott Bessent Holds a Fraud Task Force Press Conference in St. Cloud, Minnesota

What do you think? I approached this without using Transitions from the Parent Widget? Everything is independent of the other. Only the button has a Hero. #Flutter #Animations #Tasks #UI

New Flutter UI challenge That button animation at the end is so sick!!!! How would you approach building this?

I'm a big fan of checklists, but this is an interesting insight. Love the suggestion that checklists should be built toward specific outcomes. #checklist #todo #tasks #planning

▲ Microsoft just open-sourced Agensh, a multi-agent harness that runs up to 1,024 coding agents with no lead agent in charge. The key idea is self-organization. Every worker runs the same loop: gather context, claim a sub-task, build, verify, merge. They coordinate through a shared Gitea repo, a Mattermost channel and a shared findings board, instead of an orchestrator. On the 5 hardest ProgramBench tasks (GPT-5.6-sol, 6 hours, offline), the mean test-pass rate rose from 19.31% with 1 agent to 28.78% with 128 agents. On pandoc, 1,024 agents hit 55.06%, up from 33.89%. With GPT-6.1-sol, 32 agents reached 79.59%. It is a trade-off though: going from 1 to 8 agents added only 1.37 points on the 5-task mean, and token cost is not disclosed. The full harness, launch scripts and reproduction guide are on GitHub under the MIT license. It runs on Linux with Docker Compose...... Full analysis: Repo: Paper: Project: @MSFTResearch @msdev @msdev

Jobs are modeled as bundles of tasks. But as jobs change, how do we keep those task lists up to date? Workers often experience new responsibilities and tools before they reach their job descriptions. We start by listening to them. 🧵

THIS IS F*CKING INSANE Anthropic turned Agent Skills into an open spec and GitHub filled up with ready-made Claude Code teams for free one of these repos alone ships 135 agents, 35 skills, 42 commands, 176+ plugins and 20 hooks. another hands you 100+ specialized subagents. none of it costs anything 10 GitHub projects you should open first: 01 wshobson/agents → a plugin marketplace that installs the same agents into Claude Code, Codex, Cursor and Copilot, so your setup survives switching tools 02 VoltAgent/awesome-claude-code-subagents → 100+ specialized subagents covering most of what a normal engineering week throws at you 03 rohitg00/awesome-claude-code-toolkit → 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks and 14 MCP configs in one place 04 anthropics/skills → the official Agent Skills repo. start here to see the shape of a working SKILL.md before you copy anyone else's 05 netresearch/claude-code-marketplace → curated skills on an open standard, portable across Claude Code, Cursor, Copilot, Codex, Gemini CLI and 30+ other agents 06 disler/claude-code-hooks-mastery → the hooks reference. this is where you learn to make the agent stop on your rules instead of stopping to ask you 07 karanb192/claude-code-hooks → an installable hooks marketplace split into safety, cost, observability and productivity 08 affaan-m/claude-swarm → multi-agent orchestration that decomposes the task, coordinates the agents and shows the whole run in a terminal UI 09 am-will/swarms → orchestration shipped as skills, so the coordination loads only when the job actually calls for it 10 eugeniughelbur/obsidian-second-brain → persistent memory as plain markdown in an Obsidian vault, shared across Claude Code, Codex and six other agents give the first team a job with an obvious finish line: one reviewed PR, one researched brief, one failing test turned green then look at how much of that output you actually kept, and what it cost to produce. a bigger roster earns its place when it moves that number the download is free. paying four agents to repeat the same investigation is not save this before you spend another weekend building a config that already exists the article below shows how to keep context small, reuse finished work and contain retries, so more of your budget reaches the finished result ↓

SpaceXAI dropped a 2-page PDF on the best GrokBot use cases call me crazy but i'll keep saying this - read it and you'll use GrokBot better than 95% of people what the bot is which use cases actually work today how to deploy it without burning trust step 1 - every working use case has one shape read, check, apply a rule, write a draft if your task fits, the bot takes it step 2 - five checks before handoff repeatable, cross-system, rule-based, draft-first, cheap to get wrong fails one? add a gate or wait step 3 - start with sales 36 LinkedIn drafts queued overnight, zero sent without review no team has more agent-ready work step 4 - engineering gets bug repro, CI/CD watch and dependency audits the bot grabs the ticket, hits staging and hands back a repro pack step 5 - operations takes over inbox, expenses and travel the bot logs into portals with no API finance gets 8-12 hours back at month-end step 6 - marketing owns 13 of the 56 roles paid media, content calendars, competitor watch all overnight, all draft-first step 7 - the approval line every documented use case stops before external action nothing gets sent, booked or paid without you step 8 - roll out over four weeks watch, review everything, review flags, then scheduled routine skip a week and the risk stacks up step 9 - the fleet Chief of Staff bot on top, specialists below, bots messaging each other you stop being the middleman step 10 - rank tasks by the cost of a mistake the bot nails 49 in a row then does something strange on the 50th with full confidence keep a human at every exit the result - 56 roles, one playbook the bot takes the 80% that repeats you keep the 20% that matters use cases: marketplace:

stop feeding GrokBot questions start feeding it your to-do list 100 tasks you can hand off today: > research > content > operations > analysis > communication > coding > monitoring > support > planning > creative plus a prompt formula, automation ideas and approval checkpoints 100 tasks 10 categories one sheet save this before you do the next task yourself ↓

You earned the points. Now they could earn you a reward. 🎁 We’re giving 15 winners 20 USDT each from a 300 USDT pool. Have 500 confirmed GetRef Points on your balance when the giveaway ends to enter automatically. Previously earned points count, and nothing gets deducted. Need more points? • Complete exchange tasks: register through the GetRef task link and submit your new account’s UID. Old accounts don’t qualify. • Invite friends: earn 20 points per signup, plus 20% of their approved task points. Closes 7 days after this post. Winners are chosen randomly, one prize per person. If fewer than 15 qualify, they share the full pool equally.

Let's do this properly 😏 Start with your first task.. #tasks #obedientsubs #latexmodel

CAPTURED: 6 @FBI Most Wanted Fraudsters tied to $2 BILLION in alleged fraud against American taxpayers. They will now face justice. 🇺🇸 The Trump-Vance Administration will not allow criminal fraudsters to rob hardworking Americans—we will chase you to the ends of the earth.

SIX of the FBI’s Most Wanted Fraudsters. CAPTURED. Four continents. Over 4,000 combined days on the run. More than $2 BILLION tied to the FBI’s Most Wanted Fraudsters list alone. These fugitives thought crossing international borders and hiding overseas would put them beyond the reach of American law enforcement. They were wrong. This FBI and our international partners will pursue those who defraud Americans, no matter where they hide. JUSTICE WILL FIND YOU.

THIS IS A PURE F*CKING GOLD. 9 OF THE MOST-STARRED GROK BOT SETUPS ON GITHUB HAVE OVER 20K ★ BETWEEN THEM each one fixes something your bot keeps getting wrong. all 9 are FREE to download 01 / it keeps getting stuck reading websites web-access (9,281★) a web-access playbook that chooses between fetching pages, browser interaction, and other available channels. saves site-specific methods for future runs 02 / it can discuss your project but can’t work in it devspace (5,299★) connects Grok Bot to approved project folders through MCP, with tools for searching files, editing code, and running commands 03 / every task starts with you explaining everything again obsidian-second-brain (4,990★) a dedicated Grok Bot build for working with your notes, plus a shared crew logbook that records completed jobs and lessons 04 / your agents work separately and lose the handoff openmeld (1,400★) a shared workspace for people and agents to coordinate tasks, preserve context, and pick up work another teammate started 05 / it repeats the same browser clicks every run unbrowse (810★) turns authorized browser workflows into reusable API access, giving your bot a direct route when repeating the interface is unnecessary 06 / you keep discovering the same setup mistakes grokbot-field-notes (638★) rules, role descriptions, and playbooks from the Grok Bot team’s 72-hour public build, including 40 failures and the lessons behind them 07 / it builds another assistant that already exists awesome-grokbot (432★) a searchable catalog of public Grok Bot templates with checked share links and creator attribution. find a starting point before writing another setup 08 / your trading bot jumps from an idea straight to an order hypergrok-trading-desk (212★) 7 specialist roles and 17 skills separating research, strategy, risk, and review. execution requires a connected API wallet and approved trade tickets 09 / managing the bots becomes another manual job grok-bot-cli (137★) create and update bots, manage groups, send tasks, inspect conversations, and automate cleanup from scripts connected to your account pick the problem you recognize from your last session. connect the required tools and test one complete job before expanding the setup save this. fix what keeps breaking before adding another bot the article below explains 7 workflow changes that reduce repeated context, duplicate research, and failed retries so your Grok Bot setup costs less to run ↓

THIS IS AN ABSOLUTE F*CKING GOLD Anthropic just revealed one of the sharpest setups for Claude Code The idea: run autonomous agent teams across Opus 5.5, Sonnet 5.5, and Haiku 5.5, while keeping Fable 5.1 on call as adversary Zero coordinator bottlenecks and way fewer tokens: teammates talk directly over peer-to-peer mailboxes and claim tasks on their own You just launch Claude Code like this: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 claude --model opus here's how it splits: → Opus 5.5 acts as team lead: breaks epics into a shared task list, arbitrates conflicts, and signs off on pull requests → Sonnet 5.5 powers builder teammates: hammers out frontend and backend modules in parallel, messaging peer-to-peer without coordinator drag → Haiku 5.5 swarms lightweight scouts: maps AST call sites, audits dependencies, and verifies API specs at 340 tok/s → Fable 5.1 monitors the peer bus on call: audits cross-session messages and catches subtle edge cases before code merges → you stop burning Opus context on routine implementation loops and keep the lead session lean Fable 5.1 only steps in at three moments: → before a contract locks: does the frontend payload match the backend schema? → when a test breaks twice: are we fixing the root cause or just patching symptoms? → before calling it done: what security hole or invariant did everyone overlook? Opus leads · Sonnet builds · Haiku scouts · Fable challenges JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 coordinates the team and manages the shared task list at ~/.claude/tasks/ > Sonnet 5.5 runs builder teammates with direct peer-to-peer mailboxes at ~/.claude/teams/ > Haiku 5.5 runs fast scout teammates at 340 tok/s with zero coordinator lag > Fable 5.1 stays on call as adversary to challenge contracts and audit diffs > task dependencies unblock automatically as teammates mark work complete > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Enable autonomous agent teams by setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json 2. Run the main lead session on Opus 5.5 to manage architecture and the shared task list 3. Spawn Sonnet 5.5 teammates for feature builds and Haiku 5.5 for 340 tok/s repo sweeps 4. Keep Fable 5.1 on call as adversary to audit peer-to-peer messages and test failures 5. Add one rule to CLAUDE.md: teammates must consult Fable before locking API contracts, after two test failures, and before final PR sign-off 6. Route fast deterministic forks through JEV, show all changes as diffs first. No edits until I say go" ↳ save it, you'll use this every single day

I still don’t understand why people build Opus 5.5 setups from scratch. 10 repos already did it for you, from 68K stars to 0. 01 claude-code-best-practice → 68K stars. the full guide to subagents, skills, hooks, MCP and memory, with working examples 02 claude-skills → 28K stars. 388 ready skills across 20 fields, built for Claude Code, Codex and Gemini CLI 03 awesome-claude-code-toolkit → 2.7K stars. 135 agents, 42 commands, 20 hooks and 15 rules you can drop into a project 04 AI-Product-Development-Toolkit → 994 stars. six planning prompts, a Next.js starter and a ready CLAUDE.md written for Opus 5.5 05 awesome-claude-video-skills → 867 stars. 300+ repos that teach Claude to make video, sorted by type 06 awesome-claude-code → 508 stars. the cleanest map of tools, plugins and usage trackers around Claude Code 07 motion-graphics-skills → 375 stars. launch-style motion graphics where every frame is code, no After Effects 08 opus-5-5-dev → 1 star. rules for long runs: define “done” first, keep a TASKS.md, end with a fixed four-part report 09 model-bump → 0 stars. scans your code for what breaks on Opus 5.5, like forced tool choice, sampling settings and prefill 10 claude-best-practices → 1 star. 29 agents, 174 skills, 58 rules and 22 hooks to copy into your project stars measure hype. fit measures results. pick one, run it on a single task, keep only what survives. save this before you upgrade, and follow for more setups like this

Harness Engineering from Scratch 🚀 Found this excellent 21K+ star GitHub repo that teaches you how to build reliable AI coding agents, from the ground up. An entire open-source curriculum with 14 lectures, 8 hands-on projects, and 8 progressive learning phases. What makes it useful is the approach: instead of just learning concepts, you gradually build the engineering environment around an AI agent, using the same real application throughout the course. What's inside: → Agent instructions and repository structure → Context management and persistent memory → Multi-session continuity and task handoffs → Task planning, scope control, and progress tracking → Testing, verification, and observability → Automated coding loops and maker-checker workflows → Graph orchestration, parallel execution, and rollback Includes practical projects, reusable templates, a harness-creator skill, and technical breakdowns of how Claude Code, Codex, Pi, and DeepSeek build their harnesses. Available in 15 languages. Perfect for software engineers and AI developers who want to move beyond prompting and understand how reliable coding agents are actually built. Completely free and open source. Here's the GitHub Repo:

Impressive NVIDIA paper on cutting agent costs. For long-horizon agent tasks, you want the capable model for the early steps and a cheaper model for the rest. Handing off in the other direction saves little or nothing. AgentBaton learns when to make that one switch from patterns in task progress. Each check has a median latency of 338 ms on one H100. Across 11 model pairs and two benchmarks, it cuts API cost by 65.9% on average while largely keeping accuracy. Some pairs gain up to 8.8 points over running the capable model alone. The handoff happens once per task, so it is easy to add to an existing agent loop. If your agent bills are dominated by a frontier model, you might want to test one capable-to-cheap handoff before building a full router. Chat with Paper:

Any dommes or brats like to bully subs while they are at work in the office? DM me, #humiliation #tasks #findom #sub #loser

A lot more goes into building a software factory than you might think. There are 7 must-haves we've landed on: - Configured as code - Central conversation history - Benchmarking tools - Factory chat - Artifacts - Computer use - Agent debugger In detail: