Agent Architecture / Foundation

Peel - The Best Uninstaller App for Macs

This video demonstrates how Peel removes Mac applications together with hidden support files that ordinary deletion can orphan. It also tours Peel's storage inspection and cleanup tools for caches, package receipts, Homebrew items, installers, duplicates, local iCloud copies, and system tweaks.

Mostly Mac12 minTranscript found

Quick learning frame

Read this before watching.

A model becomes useful when it is wrapped in a harness: tools, state, permissions, memory, routing, and verification.

New playlist item from Mostly Mac; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Skill you build: The ability to inspect and safely remove an application's associated files while identifying other reclaimable storage on a Mac.

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.

01User intent
02Model role
03Tool surface
04State and memory
05Verification loop
06Reusable operating rule

Deep lesson

Turn this video into working knowledge.

1,984 cleaned transcript words reviewed across 601 timed caption segments.

Thesis

Peel - The Best Uninstaller App for Macs teaches a practical agent harness move: This video demonstrates how Peel removes Mac applications together with hidden support files that ordinary deletion can orphan. It also tours Peel's storage inspection and cleanup tools for caches, package receipts, Homebrew items, installers, duplicates, local iCloud copies, and system tweaks.

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.

0:00

Apps Leave Remains

“One of the things I love about Macs is how rarely we have to concern ourselves with the operating system. It doesn't take much to keep it in tip-top condition, and 99.999% of the time it just works.”

Dragging an application to the Trash removes the app itself but can leave support files in visible and hidden locations, and even bundled uninstallers may not clean up everything. On a well-used Mac, these orphaned files can consume many gigabytes. Choose one installed app and list the support-file locations you would want an uninstaller to inspect before removal.

4:52

Inspect Before Removing

“an app I made myself. I vibe coded it and called it. It's one I use for my photography, but we'll use it as an example. When you click on it, you get a full list of exactly...”

Peel inventories an app's main files, hidden Library items, and related data before moving them to the Trash. Its listings can expose unexpectedly large caches, such as the demonstrated 17 GB cache for ON1 Photo RAW 2027, as well as orphan files and redundant package receipts. Open Peel's application view for one large app, note every associated category and size, and decide which data should be removed with the app.

8:23

Find Hidden Storage

“clicking on this open developer option. So, I've just got some stuff I use here when I'm vibe coding apps for my photography channel. Let's go into developer, and we can see we've got stuff like Homebrew and...”

Beyond uninstalling apps, Peel can surface developer caches, old installers and backups, duplicate files, and locally downloaded iCloud Drive copies. It can also disable Apple Intelligence and remove stored AI models, while its iCloud cleanup removes only the local copy so the cloud file can resync later. Review Peel's Space, Developer, and Installers sections, then record the three largest reclaimable items before deleting anything.

01

User intent

Start with this video's job: This video demonstrates how Peel removes Mac applications together with hidden support files that ordinary deletion can orphan. It also tours Peel's storage inspection and cleanup tools for caches, package receipts, Homebrew items, installers, duplicates, local iCloud copies, and system tweaks. Treat "User intent" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “One of the things I love about Macs is how rarely we have to concern ourselves with the operating system. It doesn't take much to keep it in tip-top condition, and 99.999% of the time it just works.”

02

Model role

Use "Model role" to locate the part of the agent harness mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 4:52, where the video says: “an app I made myself. I vibe coded it and called it. It's one I use for my photography, but we'll use it as an example. When you click on it, you get a full list of exactly...”

03

Tool surface

Turn "Tool surface" into the reusable artifact for this lesson: A one-page agent harness map with tool boundaries, state ownership, and proof signals. This is where watching becomes something you can inspect and reuse.

04

State and memory

Use "State and memory" 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

Verification loop

Use "Verification loop" 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

Reusable operating rule

Use "Reusable operating rule" 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 one-page agent harness map with tool boundaries, state ownership, and proof signals..

Example

Agent harness proof brief

Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the agent harness pattern.

Example

Teach-back module

Transform the lesson into a definition, a User intent -> Model role -> Tool surface -> State and memory -> Verification loop -> Reusable operating rule 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.
  • treating model choice as architecture
  • ignoring tool permissions
  • missing verification evidence
  • Letting the lesson drift into generic agent definitions.
  • Letting the lesson drift into model leaderboard claims.
  • Letting the lesson drift into tool list without operating boundaries.

Transcript-derived moments

Use timestamps to study the actual video.

Quality check

Do not count this as learned until these are true.

01

State the transcript-backed claim in your own words: This video demonstrates how Peel removes Mac applications together with hidden support files that ordinary deletion can orphan. It also tours Peel's storage inspection and cleanup tools for caches, package receipts, Homebrew items, installers, duplicates, local iCloud copies, and system tweaks.

02

Explain the practical stakes without hype: New playlist item from Mostly Mac; queued for transcript-backed review, topic mapping, and a practical learning artifact.

03

Map the idea onto the User intent -> Model role -> Tool surface -> State and memory -> Verification loop -> Reusable operating rule sequence and name the weakest link.

04

Produce the artifact and include the evidence that proves it: A one-page agent harness map with tool boundaries, state ownership, and proof signals.

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: Peel - The Best Uninstaller App for Macs
- URL: https://www.youtube.com/watch?v=33ekmlVaRTo
- Topic: Agent Architecture
- My current learning frame: Audit one expendable application and three storage categories in Peel, record the files and space each would remove, and then perform only the cleanup you can explain.
- Why this matters: New playlist item from Mostly Mac; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "One of the things I love about Macs is how rarely we have to concern ourselves with the operating system. It doesn't take much to keep it in tip-top condition, and 99.999% of the time it just works."
- 2:03 / Evidence 2: "folder and into the trash can. It's a simple and easily understood process and I can fully understand why Apple chose to do it that way. But the problem is that an app is not limited purely to..."
- 4:52 / Evidence 3: "an app I made myself. I vibe coded it and called it. It's one I use for my photography, but we'll use it as an example. When you click on it, you get a full list of exactly..."
- 6:47 / Evidence 4: "receipt which is used to track it by the operating system. But the fact is that you may have removed the app and therefore the receipt is no longer required and it's telling me that I have got..."
- 8:23 / Evidence 5: "clicking on this open developer option. So, I've just got some stuff I use here when I'm vibe coding apps for my photography channel. Let's go into developer, and we can see we've got stuff like Homebrew and..."
- 10:36 / Evidence 6: "install. It doesn't take out much room itself, and it'll keep your main drive free of crap. Given that it's also open source, you can enjoy all the benefits of its amazing file finding capabilities for free. Though..."

Video-aware target:
- Prompt lane: Agent harness
- Mechanism to extract: Identify what surrounding harness makes the model more useful than chat alone.
- Artifact to produce: A one-page agent harness map with tool boundaries, state ownership, and proof signals.
- Artifact must include: model role; tools; state/memory; permission boundary; verification proof

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: Identify what surrounding harness makes the model more useful than chat alone. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A one-page agent harness map with tool boundaries, state ownership, and proof signals.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: User intent -> Model role -> Tool surface -> State and memory -> Verification loop -> Reusable operating rule
   - answers to these source questions: What does the video claim the agent can do? | What surrounding system makes that claim plausible? | What proof is shown instead of merely asserted?
   - 3 concrete examples that apply the video idea to real agentic work, such as a repo-editing harness; a local research assistant; a recurring refresh agent
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: treating model choice as architecture; ignoring tool permissions; missing verification evidence
   - a checklist for the next real workflow, focused on: tool boundaries, state ownership, done signal, recovery path
   - one practical exercise with a clear done signal: Map one current coding workflow as a harness and mark the first missing proof signal.
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 "Peel - The Best Uninstaller App for Macs", not a generic Agent Architecture essay.
- Tie each harness element to a transcript anchor that names a tool, state boundary, permission, model behavior, or verification step.
- 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 agent definitions; model leaderboard claims; tool list without operating boundaries.
- 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 better model automatically makes a better agent.

The model matters, but harness design determines whether the system can act safely and repeatably.

More tools always help.

Every tool increases surface area. Strong agents have the right tools with clear permissions.

Memory means saving everything.

Useful memory is compressed, curated, and tied to future decisions.

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 one-page agent harness map with tool boundaries, state ownership, and proof signals..

A reusable artifact with a done signal and one verification step.
03

Agent harness teach-back card

Explain the agent harness 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.

Why can dragging a Mac application to the Trash fail to reclaim all of its storage?

What does Peel show before moving an application to the Trash?

What happens when Peel removes a locally downloaded iCloud Drive file?

Source shelf

Use the video as a doorway, then verify with primary sources.

DocsOpenAI Agents SDK: agents

Read this for the basic object model: instructions, tools, handoffs, guardrails, and structured outputs.

openai.github.io/openai-agents-python/agents/
DocsOpenAI Agents SDK: tracing

Use this to understand why observability is part of agent architecture.

openai.github.io/openai-agents-python/tracing/
DocsOpenAI Agents SDK: guardrails

Good follow-up for thinking about boundaries, tripwires, and tool-level checks.

openai.github.io/openai-agents-python/guardrails/
DocsOpenAI Agents SDK: handoffs

Explains delegation between specialized agents and what context gets forwarded.

openai.github.io/openai-agents-python/handoffs/
ReadingModel Context Protocol

Useful for understanding how external tools and context servers become part of the agent environment.

modelcontextprotocol.io/introduction
PodcastLatent Space: The AI Engineer Podcast

Best ongoing podcast lane for agent tooling, AI engineering, codegen, infra, and model shifts.

www.latent.space/podcast
PodcastPractical AI podcast archive

Older but still useful practical conversations on agents, AI engineering, and production concerns.

changelog.com/practicalai/