Bushmaster

@bibryam Harnesses made runs checkable. Loops make work repeatable. I'm increasingly curious whether the next layer is the task itself: a durable artifact that survives many loops, sessions, reviews, and agent runs.

@github Interesting seeing everyone optimize context acquisition and orchestration. Makes me wonder what becomes the durable artifact once the session, branch, or agent is gone: the thread itself, or a portable task-state object with decisions, evidence, verification, and next actions?

Every context switch has a cost: new window, new branch, "wait, where was I?" The GitHub Copilot app keeps the whole loop in one place from issue to merge.

@CordnerTony @hyperbrowser Interesting. Runtime governance for agents. I wonder whether contracts, drift findings, and verification evidence eventually become durable artifacts rather than staying attached to a single run.

@Bushmaster18523 @hyperbrowser Built something for myself to implement correct repo hygiene and to prevent monolith files, ended up with a rust TUI and a tarball 🤔 github.com/tonycdr-prog/a…

/harness A Claude Code plugin built for Fable 5. It runs your agent against your project, watches it break, and writes a CLAUDE. md from the actual failures. It catches wrong paths, missing scripts, and bad assumptions so your agent never hits the same wall twice ↓

8/ We’re still early, but I suspect “task state” will eventually matter as much as prompts do today.

7/ My current bet: Execution will increasingly be owned by vendors. The continuity layer may become a portable artifact that survives tools, sessions, models, and orchestrators.

1/ Over the last few weeks we've seen: - Goals - Dynamic Workflows - Background Agents - Chief-of-Staff patterns - Context compression research - Agent memory systems The common theme isn't execution. It's continuity.

@nickbaumann_ Interesting. The CoS thread becomes a durable working memory layer. I wonder whether the long-term artifact ends up being the thread itself or a separate task-state object that survives thread changes, compaction, and tool switches.

This has fundamentally changed how I use Codex - everything runs out of a single persistent thread (my "chief of staff") - anytime I start a new project or workstream, I have that thread spin up a new thread (because it's already found the context from slack, etc) - the CoS thread checks in on the project threads during heartbeats, and occasionally sends relevant updates from slack to that thread everything flows naturally to the top

@_catwu Dynamic workflows solve execution at scale. I wonder if we'll eventually need a task-passport artifact alongside them: objectives, decisions, evidence, dead ends, and next actions that survive handoffs between agents, sessions. Execution scales. Continuity still needs a home

Excited to share our most powerful new Claude Code feature: dynamic workflows! Mention "workflow" in a prompt and Claude will dynamically create an orchestration plan that it strictly follows, allowing you to confidently trust that every stage happens in the right order even across 100s of agents.

@omarsar0 /goal + durable Task Passport feels like a strong combo for long-running agent work. Execution is one side; preserving verified task state across sessions/tool switches is the other. github.com/ihorponom/agen…

/goal is really insane! It's how you can get the most out of coding agents today. For efficiency, I find it works best when you do planning before /goal. This ensures the agent has the right context and goal, which often only happens with careful planning.

@DanielMiessler It makes me think workflow execution and workflow continuity are becoming separate layers. Vendors will own execution/orchestration. Projects like Agentpack explore the durable continuity side: github.com/ihorponom/agen… Portable task state, checkpoints, evidence, handoffs.

Claude Code is about to release a feature called /workflows that I think will be extremely significant. Especially for Enterprise AI. I talked about this in 2024 in a post called Companies Are Just Graphs of Algorithms. Basically the idea is that all work is just an algorithm, i.e., a series of steps to accomplish a goal. Skills and Cowork have been heading in this direction already, and we've seen what that's done to company valuations in various spaces. Well this is closer to the final form. It's turning the regular, expected work that's done in companies into pseudo-deterministic workflows that follow defined SOPs. The human role will be determining what problems to solve (taste, expeirence, etc), building new products from that, and then optimizing these workflows from above. But the work itself will be these workflows executed according to SOPs.

@Saboo_Shubham_ Check, slightly different layer: github.com/ihorponom/agen…⁠ Focused on durable task state across compaction, new chats, tool switches, and handoffs - preserving decisions, checkpoints, dead ends, and evidence instead of just memory.

This is ACTUALLY context engineering for your AI coding agents. It turns any codebase into an interactive graph your agent can query. Works with Claude Code, Codex, Antigravity. 100% Opensource.

@heyblake Built an open-source repo-native continuity layer for coding agents: github.com/ihorponom/agen…⁠ Focused on durable task state across compaction, new chats, tool switches, and handoffs - preserving decisions, checkpoints, dead ends, and evidence instead of just 'memory'.

Drop your project URL Let’s drive some traffic

@0xCodez Check. Built an open-source repo-native continuity layer for coding agents: github.com/ihorponom/agen…⁠ Focused on durable task state across compaction, new chats, tool switches, and handoffs - preserving decisions, checkpoints, dead ends, and evidence instead of just 'memory'.

@rauchg Built an open-source repo-native continuity layer for coding agents: github.com/ihorponom/agen…⁠ Focused on durable task state across compaction, new chats, tool switches, and handoffs - preserving decisions, checkpoints, dead ends, and evidence instead of just 'memory'.

Show me the thing you’ve built with AI you’re most proud of. Reply with a working product URL and what model / agent you primarily used.