Developer Concludes Plan Mode No Longer Necessary as AI Models Improve
A developer who built an app around AI planning says the feature has become obsolete as models get better, sparking debate over whether the shift poses risks.
What to know
- Developer and Nuanced founder Ayman Nadeem argues plan modes in AI coding tools are now obsolete as models improve at following instructions, though maintaining developer understanding becomes more critical.
- Anthropic's Claude Code team agrees plan mode is no longer essential; their implementation was merely a text reminder, never integrated into the tool's actual capabilities.
- The developer community is split: some report building custom MCP servers and spec-driven workflows to replace plan mode, while others defend it for error-catching, multi-agent review, and preventing scope creep.
- Core disagreement centers on whether plan mode's limitations reflect inherent obsolescence or fixable design flaws—and whether the real need is better real-time visibility into AI-generated work rather than upfront planning.
The dispute Whether plan mode's decline reflects improved model capabilities making it unnecessary, or poor tool implementation that better design could fix—and whether the real concern is obsolescence or loss of developer oversight. · positions read across 105 posts and comments
Plan mode is obsolete; better models understand context well enough without it, and interactive iteration is a superior replacement.
-
“I broadly agree with the author's point: plan mode was useful, and is no longer useful.”
bcherny · Hacker News ↗
Plan mode remains valuable for preventing errors, maintaining developer understanding, and catching AI hallucinations before they propagate.
-
“I don't agree. I think the way maybe the author used planning to maintain an understanding of the changes is largely not necessary, but there are other good use cases. For example, it's a great hook in the process for agentic review.”
Bockit · Hacker News ↗
The problem isn't plan mode itself but its implementation; better tool design (change diffing, read-only execution, proper versioning) would make it far more useful.
-
“seems like plan mode could turn off some tools, even if it doesn't change the set offered to the model…isn't the right way to know if plan mode helps or not, to run an experiment? we're all guessing unless we have data”
bionhoward · Hacker News ↗
The real risk is developers losing understanding and accountability; code generated at scale without human review is dangerous regardless of plan mode's utility.
-
“I'm actively watching understanding slip away from developers, code review getting paired down to no comment checkmarks, and codebases go to bloated messes that nobody can read.”
taurath · Hacker News ↗
Ayman Nadeem Developer, founder of NuancedBen Cherny Claude Code developer at Anthropicbcherny Anthropic team member
How it unfolded 6 developments, newest first · click a bar or a number to jump articlespostscomments
-
6
Commenter identifies successor to plan mode: real-time state visualization
A developer argued the real problem is that LLM harnesses lack visibility into system state as work proceeds. Rather than planning upfront, the next tool should automatically provide developers with simple diagrams and status summaries, allowing them to verify progress without manual prompting.
“IMO the current successor to plan mode should be the harness knowing when to tell the use "ok here's our overall current state in a simple diagram", auromatically…”
— zobzu -
For an adhd mind that serial interface is a bless and hell at the same time. Great for the detailed planning discussion, bad for checking the results.I am currently working on canvas-based interfaces for that reason and i would think the only way to really create value here is with a deep independent analysis and visualization of the changes…
2 more of the top 3 · 71 posts in this stretch
-
N
Plan mode is dead: https://www. aymannadeem.com/artificial/int elligence,/developer/tools/2026/09/24/plan-mode-is-dead.html Discussion: http:// news.ycombinator.com/item?id=4 9840054
-
I still rely heavily on plan modes, first to think through product design from the 3-sentence descriptions handed to me as super-complex feature requests, and second to implement the technical requirements I want to build. Way before AI, I think the first idea, while sparked by inspiration, has always created a local minimum and suggested that…
-
-
5
Developers defend plan mode for error-catching and code review
Several commenters pushed back on the essay's conclusions, arguing plan mode remains valuable as a checkpoint for catching bugs and for multi-agent review workflows. Others noted that as task complexity and scope grow, iterative development with intermediate code spikes may replace detailed upfront planning entirely.
“Get a second agent to look at what will be implemented and check it for inconsistencies…It surfaces a large number of opportunities for refinement.”
— Bockit -
I disagree with the assertion that the model gets it. Here’s a practical example I just tried with Fable 5.1. I gave it this prompt: “Write a Go function that can be used to establish secure communication to a remote system using a certificate. Keep it short, single function, and explain how to use it.” The output forced the use of a private key…
2 more of the top 3 · 11 posts in this stretch
-
H
Plan mode is dead Link: https://www. aymannadeem.com/artificial/int elligence,/developer/tools/2026/09/24/plan-mode-is-dead.html Discussion: https:// news.ycombinator.com/item?id=4 9840054
-
I'm using a set of skills for planning now which does something similar to plan mode but it's creating documentation that later skills reference it while building. It works so much better than anything else I've tried, because it keeps things on track throughout the feature buildout and across different agents/models/tasks. From what I read here…
-
-
4
Debate emerges over whether plan mode drawbacks are design flaws
Commenters disputed whether plan mode's limitations stem from models improving or from poor implementation. Some argued plan mode still helps stabilize complex workflows and catch errors, while others said the tool lacks features (like read-only command execution or proper change diffing) that would make it effective.
“seems like plan mode could turn off some tools, even if it doesn't change the set offered to the model…isn't the right way to know if plan mode helps or not, to run an experiment? we're all guessing unless we have data…”
— bionhoward -
> This worked well for a while, until a few months ago, using early versions of Fable, I realized that I wasn’t using plan mode anymore because the model just got it, and because for the increasingly complex work I asked the model to do, planning had become interactive and iterative. With Opus 5.5, I feel Opus has gotten to that point too.For me…
2 more of the top 3 · 6 posts in this stretch
-
> plan mode has always been a prompt — it has never changed the toolset because doing so would break the prompt cache, and so would be expensiveseems like plan mode could turn off some tools, even if it doesn't change the set offered to the model, the ones that they have which would mutate your codebase could just not work with an error message…
-
For me the most useful thing about plan mode in Claude or Codex is not the plan, I usually barely read it, it's that it forces models to gather as much context as possible before implementing. Without plan mode models tend to implement wrong solutions because they are reading not enough context before writing code.Of course this can be done with…
-
-
3
Developers report workarounds replacing plan mode with custom tools
Multiple developers in the discussion described building their own systems to replace plan mode. Some created MCP servers with micro-skills, others adopted spec-driven documentation workflows, and several now use custom prompting approaches—suggesting the dev community is moving beyond built-in plan mode toward bespoke solutions.
“I ended up building out tool an MCP server that I use as a bit of a psuedo harness for Claude…to get Claude to think in a repeatable and reliable manner.”
— SkyPuncher -
Plan mode was great, but I realized I progressed well beyond it. I found that I was getting these categories repeated errors and oversights from Claude (and frankly it hasn't gotten much better about this). Skills were too generic and got lost to context.I ended up building out tool an MCP server that I use as a bit of a psuedo harness for Claude…
2 more of the top 3 · 4 posts in this stretch
-
I'm probably just behind the curve, but I still use plan mode quite a bit in Claude Code. I iterate on the plan repeatedly until it largely agrees with what I want. Once it seems good I ask it to build the plan and open a PR when done.My only critic of the plan mode is I wish it was easier to see the updates and changes easily in Claude Code as we…
-
Using an LLM for any large project shows how useful it is to have data and functions that aren't siloed. That's why CLI apps have had a resurgence: because the LLM can interface with them. Yet the reaction from so many who are deep into LLM development is to build their own little silo: an app.We really need a better model. One alternative is to…
-
-
2
Nadeem clarifies distinction between two purposes of plan mode
Nadeem replied in the discussion to explain his core distinction: making agent instructions precise (now less necessary as models improve) versus helping humans understand outputs (becoming more important, but plan modes are the wrong interface for it). He noted his focus has shifted to interactive, iterative approaches.
“Where I've changed my mind is the interface for #2. I increasingly think an interactive, iterative work…”
— aymandfire -
I'm actively watching understanding slip away from developers, code review getting paired down to no comment checkmarks, and codebases go to bloated messes that nobody can read. Axioms like engineers must understand and take responsibility for the code they ship are getting torn down, and the products coming out are reflecting conway's law…
2 more of the top 3 · 7 posts in this stretch
-
hi I’m the author of the post. I think that’s basically the distinction I’m trying to make.Historically, plan mode served two different roles:1. making the agent’s instructions precise enough to execute 2. helping the human understand what was about to happenI think #1 is less necessary as agents get better. #2 is going the other direction, it…
-
When I draft my idea for the implementation of a feature or bug fix, I don't even trust a _human_ to understand what I mean the first time. There are _always_ either errors on my part, or erroneous assumptions on theirs. Everything from "this accounts for X and Y, but not Z which breaks the whole thing" to "this part of the idea directly…
-
-
1
Anthropic's Claude Code developer agrees plan mode is obsolete
Ben Cherny, who works on Claude Code at Anthropic, responded to the essay agreeing that plan mode has become less useful. He revealed that in Claude Code, plan mode is merely a text reminder to not code yet—never a change to the toolset—implemented late one night and kept for simplicity's sake.
“I broadly agree with the author's point: plan mode was useful, and is no longer useful.”
— bcherny -
2 outlets Plan mode is dead
first by HN Frontpage, 2d ago · also HN Best
-
[I work on Claude Code] I broadly agree with the author’s point: plan mode was useful, and is no longer useful.In Claude Code, all plan mode does is add a little reminder to every user message along the lines of “you’re in plan mode, please don’t code yet”. It’s something I came up with late on a Sunday night many months ago, when I got tired of…
2 more of the top 3 · 6 posts in this stretch
-
H
Plan mode is dead L: https://www. aymannadeem.com/artificial/int elligence,/developer/tools/2026/09/24/plan-mode-is-dead.html C: https:// news.ycombinator.com/item?id=4 9840054 posted on 2026.09.24 at 23:59:11 (c=3, p=9)
-
Claude code’s plan mode began its slow march towards deprecation when they hid the “clear context and implement” option behind a flag. From the discussion at that time it seemed that the developers considered it mostly a legacy feature, and that newer models are smart enough in long context not to need it.
-
-
background
Nadeem publishes essay declaring plan mode obsolete — Ayman Nadeem posted an essay on his blog arguing that plan modes in AI coding tools, once essential for directing agents and maintaining developer understanding, have become less useful as models improve. He built Nuanced, a desktop coding app centered on planning, but concluded the approach failed and that plan modes broadly serve diminishing purposes.
What people are saying 13 voices from 1 site · best of 105 · verbatim
- What replaces plan mode as the interface for developers to maintain understanding of complex, rapidly changing codebases?
- Should AI coding harnesses provide automatic state summaries and change visualizations, and if so, what would that look like?
- How do developers at scale verify correctness and maintain accountability when AI agents generate thousands of lines without explicit review?
- Yesterday
-
So my Claude Code workflow for a ticket is:* Scoping discussion - do research and figure out approach (auto mode)* Planning - take the scoping and convert it to a concrete plan for review (plan mode)* Implementation - put the plan into action (auto mode)I find this works really well for my workflow, and it is really easy to trigger each phase…
-
> In Claude Code, all plan mode does is add a little reminder to every user messageI was quite surprised when I learned this (when Claude Code edited a file despite being in plan mode). I had previously assumed "plan mode" was a harness level concern, and restricted what tools could be used. I didn't expect that it was simply an addendum to the…
-
I still find plans to be useful for big changes. I first ask to create a plan for the specific feature i have in mind. Then i ask for a second round of research with the current project in mind. Then i ask if it can make improvements on the plan. Then i read the plan and note issues down and let it correct them.In my experience the problem with…
-
Good to hear, this is my experience also:I haven't reached for Plan Mode in awhile--maybe, on some blank folder/canvas and I just want that cute "questionnaire" DX to get me going...But on the whole, CC is smart enough to know when to "rush off and act" and when to "pushback", which is great--and it's no big deal to tell it to pause/stop by adding…
-
What I do nowadays, for large changes, is have Fable create a HTML explainer for what we're gonna do with code snippets, which is not that fat from plan mode only much more convenient for me and modern models have no issue using that HTML artifact as the source of truth, and then before I get into execution - I interactively build an end to end…
-
I once tried to build something similar to your product on top of Codex, and I failed.But my conclusion on plan mode is slightly different. I agree that plan mode itself may be a dead end, but I still believe there might be another way to achieve the same goal.When I was building my product, I found that the biggest issue wasn't capability, but…
-
Fascinating piece, puts in words what I've been feeling for a while..Over time I found some useful patterns (indeed after not getting what I want from plan mode), but this piece convinced me to double down on them and always try to find (and let the LLM construct) clarifying abstractions that have a deterministic relation to the code.2 examples I…
-
So planning is tied to the spec. This much is clear.What the author I think is hinting at is not planning alone but "the development and evolution of any program and the state of this program throughout the planning, elaboration, and eventual runtime".I chuckle at the thought that throwing an md file or a prompt at this problem is sufficient.So, I…
-
Anecdotally, in the Opus 4.6 days, it felt like there was something special about using plan mode to discover the approach then clearing the context to execute on it.A mixture of defending against a disastrous mid-implementation compaction (where suddenly things would veer off the rails) and also allowing the fresh execution to double-check the…
- Sep 25
-
Yeah I think this is a natural consequence of longer task horizons. When I was chaining 4h tasks, I can mostly plan them up front.Now that I’m frequently designing and delegating day/week scale features, the flow has to change; having the agent go off and build a spike can be a quicker way of us understanding the design space and constraints…
-
Maybe, I always say "let's write a plan and refine it" which ends up being a nice rubber duck session to keep claude and friends from going off the rails implementing things like privacy or encryption or some other rabbit hole when I just need it to do a few features at a time so I can review while it starts the next few things. Maybe this is…
-
> plan mode was useful, and is no longer useful.> In Claude Code, all plan mode does is add a little reminder to every user message along the lines of “you’re in plan mode, please don’t code yet"Can't help but think if plan mode isn't useful as you say because it's implementation is lacking in claude code, hypothetically speaking.What I can say is…
-
For work, I primarily use Gemini CLI, and the one real awkward part of plan mode is that the harness can't run commands, even exploratory ones. So when I'm giving the harness a task in plan mode, it can't experiment and is either blind or relying on its training data and/or any other context (e.g. source code, documentation) I give it. And it…