Bret Fisher explains why he replaced Ghostty/iTerm with Supacode, a libghostty-based 'agent harness session manager' for macOS that keeps the terminal primary while adding a project sidebar, GitHub PR/check awareness, agent hooks for Claude Code and friends, simple git worktree management, and ZMX session persistence.
Bret Fisher23 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from Bret Fisher; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to evaluate terminal-first agent session managers against pure-GUI alternatives and pick a setup that tames dozens of concurrent agent-harness sessions without abandoning the shell.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
4,518 cleaned transcript words reviewed across 1,210 timed caption segments.
Thesis
My new terminal daily driver: Supacode for macOS teaches a practical coding-agent workflow move: Bret Fisher explains why he replaced Ghostty/iTerm with Supacode, a libghostty-based 'agent harness session manager' for macOS that keeps the terminal primary while adding a project sidebar, GitHub PR/check awareness, agent hooks for Claude Code and friends, simple git worktree management, and ZMX session persistence.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:53
Harness, not just agent
“harnesses, agent harnesses like cloud code and codeex and co-pilot and all the other wonderful ones, the pies, the open codes, the Hermes, the open clause, these are all primarily right now at least TUIs first or TUI...”
Tools like Claude Code, Codex, and OpenCode are agent harnesses — an agent is the combination of permissions, model choice, system prompt, and tools, and one harness contains many of them — so the real problem is 'tab hell': dozens of terminal tabs holding session state you can't afford to close. Write down the four components (permissions, model, system prompt, tools) for two agents you actually run, then count how many live harness sessions/tabs you kept open this week.
7:45
Sidebar as abstraction
“different sessions. But it did have a web preview which is pretty slick although I don't really tend to use that. But somewhere in the early first quarter of this year I learned about Superode and Superode is...”
Supacode adds a project/directory sidebar on top of normal tabs and panes — plain folders work, not just git repos — with per-project colors, pinning, branch display, and GitHub integration (via OAuth or the gh CLI token flow) that surfaces PR status and failing checks in a title-bar notch without visiting the PR page. Add your three most-used directories (including one non-git folder) to a session manager or terminal profile, pin the hottest one, and note whether branch/PR state is visible at a glance.
15:32
Agents drive the GUI
“running in the app is managing the app itself. And the thing that I use it the most for is when I'm already in an agent and I just tell it, hey, could you open up this directory...”
Supacode ships its own CLI meant for the agents themselves — from inside Claude Code you can tell it to open a directory as a new project or create git worktrees (it made worktrees finally click for Bret), and ZMX support keeps sessions like Claude Code running in the background across app restarts, tmux-style. Try the worktree flow: set a worktree location, create a branch-plus-worktree from the UI or via an agent, and confirm you can hop between three checked-out branches of one repo.
01
Inspect context
Start with this video's job: Bret Fisher explains why he replaced Ghostty/iTerm with Supacode, a libghostty-based 'agent harness session manager' for macOS that keeps the terminal primary while adding a project sidebar, GitHub PR/check awareness, agent hooks for Claude Code and friends, simple git worktree management, and ZMX session persistence. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:53, where the video says: “harnesses, agent harnesses like cloud code and codeex and co-pilot and all the other wonderful ones, the pies, the open codes, the Hermes, the open clause, these are all primarily right now at least TUIs first or TUI...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 7:45, where the video says: “different sessions. But it did have a web preview which is pretty slick although I don't really tend to use that. But somewhere in the early first quarter of this year I learned about Superode and Superode is...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Verify behavior
Use "Verify behavior" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Bret Fisher explains why he replaced Ghostty/iTerm with Supacode, a libghostty-based 'agent harness session manager' for macOS that keeps the terminal primary while adding a project sidebar, GitHub PR/check awareness, agent hooks for Claude Code and friends, simple git worktree management, and ZMX session persistence.
02
Explain the practical stakes without hype: New playlist item from Bret Fisher; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: My new terminal daily driver: Supacode for macOS
- URL: https://www.youtube.com/watch?v=98CM_Yq867c
- Topic: Interfaces + Open Design
- My current learning frame: Install Supacode (or a comparable libghostty session manager), migrate your five active projects into its sidebar, enable hooks for one agent harness, and run a two-branch worktree experiment to see whether it beats your current tab-per-session workflow.
- Why this matters: New playlist item from Bret Fisher; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:53 / Evidence 1: "harnesses, agent harnesses like cloud code and codeex and co-pilot and all the other wonderful ones, the pies, the open codes, the Hermes, the open clause, these are all primarily right now at least TUIs first or TUI..."
- 5:40 / Evidence 2: "So there's many agents that you can put into cloud code. They all do a little bit different things. And to me, an agent is four things. It is the combination of permissions of what it can do,..."
- 7:45 / Evidence 3: "different sessions. But it did have a web preview which is pretty slick although I don't really tend to use that. But somewhere in the early first quarter of this year I learned about Superode and Superode is..."
- 9:53 / Evidence 4: "is a new layer of abstraction on top of that. So for each one of these projects, and it doesn't have to be a Git project, which is key. There's lots of other apps out there that use..."
- 15:32 / Evidence 5: "running in the app is managing the app itself. And the thing that I use it the most for is when I'm already in an agent and I just tell it, hey, could you open up this directory..."
- 18:13 / Evidence 6: "that it does that. So when I'm ever in a cloud code session, it rises to the top so I can focus the top of the list rather than all the other projects that are maybe something that..."
- 20:30 / Evidence 7: "recently learned about. It's a pretty sexy looking app. I admit it looks really good and it's only for Open Code. So, if you're someone who's into the Open Code, I've got videos on this channel about Open..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "My new terminal daily driver: Supacode for macOS", not a generic Interfaces + Open Design essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
A beautiful page is automatically a good learning tool.
Learning requires sequence, active recall, feedback, and application.
Generated UI should be accepted as-is.
Generated UI needs critique, revision, and browser verification.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
According to the video, what four things combine to make an 'agent' inside a harness like Claude Code?
How does Supacode show GitHub pull request and CI status without you visiting the PR page?
What does Supacode's ZMX support give you when you quit and reopen the app?
Source shelf
Use the video as a doorway, then verify with primary sources.
